Chemical fiber paper tube production quality inspection method and system

Abstract

The present application provides a method and system for quality inspection of chemical fiber paper tube production, which relates to the field of quality inspection technology, including: connecting a data acquisition module to obtain real-time monitoring data of a production line; integrating and storing real-time monitoring data, preprocessing monitoring data in a production database, and establishing a process data block; parsing production quality grade parameters, and building an adaptive quality inspection module; extracting data according to the process data block and importing it into an adaptive quality inspection module, matching and analyzing through multiple quality grade channels, obtaining quality inspection results for process positioning according to process node labels, and sending corresponding processing instructions or product scrapping feedback based on process positioning. This application can solve the technical problem of the lack of in-depth mining of the correlation between various process nodes in the production process in the prior art, and achieve the technical effect of improving production efficiency, reducing resource waste, and ensuring stable product quality and traceability.

Description

Technical Field

[0001] The present application relates to the technical field of quality inspection, and in particular to a method and system for inspecting the production quality of chemical fiber paper tubes. Background Art

[0002] In modern manufacturing, quality control has always been a key link to ensure that products meet standards and meet market demand. Although existing quality control systems have introduced sensors and automated detection technologies, most of them rely on static models and a single detection method, lacking in-depth exploration of the correlation between various process nodes in the production process. Many quality detection systems can only detect specific process links. Once a quality problem occurs, it is often impossible to trace it back to the specific process node or parameter, resulting in the inability to make targeted improvements. For example, some process control systems may only be able to detect a single parameter such as temperature or pressure in a specific process, but these single parameters are often difficult to accurately reflect the quality changes in the entire production process. Moreover, in some cases, although the detection system can detect anomalies, their feedback mechanism is not intelligent enough and cannot automatically adjust production parameters according to real-time data, resulting in low production efficiency and waste of resources. In addition, traditional quality detection systems are mostly offline analysis modes, and product samples usually need to be sent to the laboratory for testing, which not only increases the time cost, but also causes a large number of delays in the production process, which cannot meet the needs of modern rapid production.

[0003] To sum up, there are technical problems in the prior art due to the quality control system relying on static models and a single detection method, and lack of in-depth exploration of the correlation between various process nodes in the production process, which leads to the inability to trace back to specific process nodes or parameters in a timely manner, and thus the inability to make targeted improvements, which further affects the production efficiency and the stability of product quality. Summary of the invention

[0004] The purpose of this application is to provide a method and system for detecting the production quality of chemical fiber paper tubes, so as to solve the technical problem in the prior art that the quality control system relies on a static model and a single detection method, lacks in-depth exploration of the correlation between various process nodes in the production process, resulting in the inability to trace back to specific process nodes or parameters in a timely manner, and thus unable to make targeted improvements, further affecting the production efficiency and the stability of product quality.

[0005] In view of the above problems, the present application provides a method and system for detecting the production quality of chemical fiber paper tubes.

[0006] In the first aspect, the present application provides a chemical fiber paper tube production quality inspection method, which is implemented through a chemical fiber paper tube production quality inspection system, including: connecting a data acquisition module to obtain real-time monitoring data of the production line, the data acquisition module is connected to a sensor arranged on the production line, and is used for real-time synchronization of sensor data; integrating and storing the real-time monitoring data according to monitoring location, data source, and monitoring time, building a production database, preprocessing the monitoring data in the production database, and establishing a process data block, wherein the process data block has a process node label; parsing production quality grade parameters according to the production process, and constructing an adaptive quality inspection module, wherein the adaptive quality inspection module includes multiple process cycle channels, each process cycle channel includes quality defect detection and scrap analysis, and reprocessing optimization analysis sub-channels; extracting data according to the process data block and importing it into the adaptive quality inspection module, performing matching analysis through the multiple process cycle channels, and obtaining quality inspection results, wherein the quality inspection results are used to perform process positioning according to the process node label, and sending corresponding processing instructions or product scrap processing feedback according to the quality inspection results based on the process positioning.

[0007] In the second aspect, the present application also provides a chemical fiber paper tube production quality inspection system for executing the chemical fiber paper tube production quality inspection method as described in the first aspect, including: a data acquisition module, the data acquisition module is used to connect the data acquisition module to obtain real-time monitoring data of the production line, the data acquisition module is connected to the sensor arranged on the production line, and is used for real-time synchronization of sensor data; an integrated storage module, the integrated storage module is used to integrate and store the real-time monitoring data according to the monitoring location, data source, and monitoring time, build a production database, pre-process the monitoring data in the production database, and establish a process data block, the process data block has a process node label; a parameter analysis module, the The parameter parsing module is used to perform production quality grade parameter parsing according to the production process, and to construct an adaptive quality detection module, wherein the adaptive quality detection module includes multiple process cycle channels, and each process cycle channel includes quality defect detection, scrap analysis, and reprocessing optimization analysis sub-channels; a matching analysis module, wherein the matching analysis module is used to extract data according to the process data block and import it into the adaptive quality detection module, and to perform matching analysis through the multiple process cycle channels to obtain quality detection results, and the quality detection results are used to perform process positioning according to process node labels, and to send corresponding processing instructions or product scrap processing feedback according to the quality detection results based on the process positioning.

[0008] The technical solution provided in the present application has at least the following technical effects or advantages: obtaining real-time monitoring data of the production line by connecting a data acquisition module, the data acquisition module is connected to the sensors arranged on the production line, and is used for real-time synchronization of sensor data; integrating and storing the real-time monitoring data according to the monitoring location, data source, and monitoring time, building a production database, pre-processing the monitoring data in the production database, and establishing a process data block, wherein the process data block has a process node label; parsing production quality grade parameters according to the production process, building an adaptive quality detection module, wherein the adaptive quality detection module includes multiple process cycle channels, each process cycle channel includes Quality defect detection and scrap analysis, reprocessing optimization analysis sub-channel; extract data according to the process data block and import it into the adaptive quality detection module, perform matching analysis through the multiple process cycle channels to obtain quality detection results, the quality detection results are used to locate the process according to the process node label, and send corresponding processing instructions or product scrap processing feedback according to the quality detection results based on the process positioning, that is, by realizing the technical goal of intelligent quality detection based on real-time data collection and analysis, through dynamic monitoring and adaptive adjustment of multiple nodes and multiple factors, the technical effect of improving production efficiency, reducing resource waste, and ensuring stable product quality and traceability is achieved.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0011] Figure 1 This is a flow chart of the chemical fiber paper tube production quality testing method of this application; Figure 2 This is a schematic diagram of the structure of the chemical fiber paper tube production quality inspection system for this application.

[0012] Description of reference numerals: Data collection module 11, integration storage module 12, parameter analysis module 13, matching analysis module 14. DETAILED DESCRIPTION

[0013] This application provides a method and system for detecting the quality of chemical fiber paper tube production, which solves the technical problem in the prior art that the quality control system relies on static models and a single detection method, lacks in-depth exploration of the correlation between various process nodes in the production process, and cannot trace back to specific process nodes or parameters in a timely manner, thus making it impossible to make targeted improvements, further affecting the stability of production efficiency and product quality. The technical goal of achieving intelligent quality detection based on real-time data collection and analysis is achieved, and through dynamic monitoring and adaptive adjustment of multiple nodes and multiple factors, the technical effect of improving production efficiency, reducing resource waste, and ensuring stable product quality and traceability is achieved.

[0014] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0015] For example, please refer to the attached Figure 1 The present application provides a chemical fiber paper tube production quality detection method, which is applied to a chemical fiber paper tube production quality detection system, and specifically includes the following steps: Step 1: Connect the data acquisition module to obtain real-time monitoring data of the production line. The data acquisition module is connected to the sensors arranged on the production line for real-time synchronization of sensor data.

[0016] Specifically, the data acquisition module is connected to obtain real-time monitoring data of the production line, and the system module for collecting data is connected to various sensors in the production line to obtain parameter data generated during the production process in real time. The data acquisition module can receive the signal from the sensor and convert it into a visual analysis result. The connection between the data acquisition module and the sensors deployed on the production line means that the module is directly connected to the sensor devices distributed at each key node of the production line through physical or wireless means. The deployment of sensors is to place the equipment in a position that can provide effective monitoring data according to the process requirements. For example, a bonding sensor is placed at the bonding point of the paper tube to detect the amount of glue applied; a temperature sensor is placed in the curing area to ensure the stability of the curing temperature.

[0017] Real-time synchronization of sensor data means that the module can continuously receive the output signal of the sensor and transmit and process the data at the millisecond level. The key to real-time synchronization is to eliminate data transmission delays so as to respond to changes in production in a timely manner.

[0018] Step 2: Integrate and store the real-time monitoring data according to monitoring location, data source, and monitoring time, build a production database, pre-process the monitoring data in the production database, and establish a process data block, wherein the process data block has a process node label.

[0019] Specifically, integrating and storing real-time monitoring data according to monitoring location, data source, and monitoring time means classifying and organizing the real-time data obtained from the production line sensors for subsequent analysis. Monitoring location refers to the sensor layout location corresponding to the data, such as the temperature sensor installed in the curing area, and the industrial camera located at the finished product exit; the data source refers to the specific sensor equipment, such as a certain model of temperature sensor or industrial camera; the monitoring time records the specific time point when the data is generated, which can ensure the time continuity and traceability of the data.

[0020] Building a production database means storing the organized data in a digital system for easy query and management. For example, storing the data of adhesive coating amount in the database according to location (bonding station), source (bonding sensor) and time (specific time point of daily detection) can form a complete historical record line.

[0021] Preprocessing the monitoring data in the production database means performing necessary screening and conversion on the raw data to improve data quality and analysis efficiency. Preprocessing includes operations such as removing outliers, filling missing data, and data standardization. For example, if a temperature sensor suddenly shows one thousand degrees Celsius at a certain point in time, this is obviously abnormal data, which can be removed through preprocessing; and the missing bonding data can be filled in through interpolation algorithms.

[0022] Establishing process data blocks means modularly grouping the pre-processed data according to the process links to make it clearer and more intuitive. A process data block can contain all relevant data for a process node. For example, the curing process block may include information such as temperature, time, and pressure. The process node label is an identifier for each block, which is used to describe the specific process location or stage to which the data belongs. For example, the curing process block can be labeled as a "curing node", while the coating process block can be labeled as a "coating node".

[0023] Step 3: Analyze the production quality grade parameters according to the production process and build an adaptive quality detection module. The adaptive quality detection module includes multiple process cycle channels, and each process cycle channel includes quality defect detection, scrap analysis, and reprocessing optimization analysis sub-channels.

[0024] Specifically, in each process of production, according to the process parameters of each step, how these parameters affect the final product quality level, including temperature, humidity, time, etc., needs to be monitored and evaluated in real time in each production step. By analyzing these parameters, we can understand the quality impact of different process nodes, and then provide a basis for subsequent quality control. Building an adaptive quality detection module means integrating the above analysis results to design a quality detection system that can automatically adjust according to real-time data. The adaptive quality detection module can adapt to changes in the production process, evaluate product quality in real time, and adjust according to different situations. The adaptive quality detection module includes multiple process cycle channels, which divide the different stages of the production process into multiple cycles, and each cycle corresponds to a process. In these cycles, each process cycle channel undertakes specific tasks to ensure comprehensive quality control at each stage. These channels include quality defect detection and scrap analysis and reprocessing optimization analysis sub-channels. The quality defect detection channel is responsible for monitoring product quality problems that may occur in the production process, the scrap analysis channel analyzes which products should be scrapped, and the reprocessing optimization analysis sub-channel optimizes the reprocessing strategy for those products that cannot directly meet the quality standards. The sub-channels work together to achieve a comprehensive and dynamic quality inspection and control system through comprehensive evaluation and adjustment. For example, during the production process, if the parameters of a process step exceed the preset range, the quality defect detection channel will immediately find the problem, and the scrap analysis channel will determine whether the product needs to be scrapped. If not, the reprocessing optimization analysis sub-channel will formulate a reprocessing plan for it, so that the final product quality meets the standard.

[0025] Step 4: Extract data according to the process data block and import it into the adaptive quality inspection module, perform matching analysis through the multiple process cycle channels to obtain quality inspection results, and use the quality inspection results to locate the process according to the process node label, and send corresponding processing instructions or product scrapping feedback based on the process positioning and the quality inspection results.

[0026] Specifically, the necessary information is extracted from the process data block and imported into the adaptive quality inspection module. The process data block contains detailed information about each process node in the production process, such as temperature, pressure, time, etc., which are helpful for subsequent quality inspection work. Matching analysis through multiple process cycle channels refers to the use of multiple quality level channels, which are responsible for analyzing production samples of different quality levels and comparing them with the process parameters in the data to determine the quality level of the current production. For example, if the quality analysis channel of a process node detects that the temperature is too high or the pressure is abnormal, the product quality is determined based on this information. After obtaining the quality inspection results, further process positioning can be carried out through these inspection results. Process positioning refers to matching the inspection results with specific production process links according to different process node labels to determine which link may have problems. For example, if the quality is found to be unqualified during the coating process, process positioning can help determine that the problem occurs in the thickness control of the coating. Based on the process positioning, the corresponding processing guidance or product scrapping processing feedback is sent according to the quality inspection results, and the processing guidance will be automatically generated or the product needs to be scrapped according to the located process node problems. If the test results show that a product cannot meet the quality standards, feedback will be given to the operator for scrapping. If the test results show that there is a potential problem at a process node, the system will provide specific adjustment suggestions or guide the operator to reprocess to ensure that subsequent products meet quality requirements.

[0027] The chemical fiber paper tube production quality inspection method is applied to the chemical fiber paper tube production quality inspection system, which can achieve the technical goal of intelligent quality inspection based on real-time data collection and analysis, and achieve the technical effect of improving production efficiency, reducing resource waste, and ensuring product quality stability and traceability through dynamic monitoring and adaptive adjustment of multiple nodes and multiple factors.

[0028] Furthermore, the present application also includes: analyzing the production process of chemical fiber paper tube production, configuring sensors in each process based on the influence of process parameters on process quality, and the sensor equipment includes temperature sensors, bonding sensors, and industrial cameras; positioning the sensors to set process nodes and layout positions, and establishing a data connection relationship between data source and process positioning; based on the data connection relationship between data source and process positioning, constructing the data acquisition module.

[0029] Specifically, chemical fiber paper tubes are special paper tubes used in the fields of textiles, chemical fibers, etc., and their production process includes steps such as raw material processing, molding, bonding, curing, and cutting. Analyze the production process of chemical fiber paper tube production, and conduct detailed decomposition and research on the entire manufacturing process of chemical fiber paper tube production. Process parameters refer to key control variables that affect production results, such as temperature, viscosity, pressure, etc. Based on the influence of process parameters on process quality, that is, the influence of different process parameters on the performance of produced paper tubes (such as strength and temperature resistance), sensors are configured in each process. Sensor equipment includes temperature sensors, bonding sensors, and industrial cameras to optimize process parameters to improve product quality.

[0030] Sensors are configured in each process to achieve real-time monitoring and recording of process parameters, ensuring the comprehensiveness and accuracy of process data. Sensor equipment includes temperature sensors, bonding sensors and industrial cameras. Temperature sensors are used to monitor temperature changes during heat treatment or curing involved in each process link; bonding sensors are responsible for detecting whether the distribution, thickness and viscosity of the adhesive meet the requirements; industrial cameras use image acquisition technology to achieve automatic detection of paper tube appearance defects (such as bubbles and cracks).

[0031] Positioning sensors to set process nodes and layout locations refers to determining the installation points and specific locations of sensors in the process flow. Process nodes refer to key steps in the production process that require parameter monitoring and control, such as the application point of the adhesive or the temperature range of curing. The layout location needs to take into account measurement accuracy, data representativeness, and the feasibility of equipment installation. For example, a temperature sensor may need to be placed in the center of the curing chamber, while an industrial camera may be installed at the exit of the finished product to detect the overall product quality.

[0032] Establishing a data connection relationship between data source and process positioning means binding the real-time data obtained by the sensor with the corresponding process node to form a clear data mapping relationship, which can achieve accurate correspondence between production data and specific process links, making it easier to track the source of parameter anomalies. For example, the reading of the temperature sensor can be marked as "curing stage temperature" in real time, and once an over-standard problem occurs, the link can be quickly located.

[0033] Based on the data connection relationship between data source and process positioning, a data acquisition module is constructed to collect, organize and analyze the data generated by the sensor, process various data types (such as temperature curves, image data) and display and store them in real time. For example, the data acquisition module can display the real-time temperature value of each node through the software interface, and record all historical data for subsequent analysis.

[0034] By analyzing the production process of chemical fiber paper tubes, configuring sensors to locate key process nodes and establishing data connections, and finally building a data acquisition module, it is possible to achieve all-round monitoring and real-time optimization of the production process, which can significantly improve product quality and production efficiency while reducing resource waste and cost expenditure.

[0035] Furthermore, the present application also includes: sorting and connecting process nodes according to the production process, collecting positive data and negative data of each process node, the positive data is sample data whose production quality finally meets the quality standard, and the negative data is sample data whose production quality does not meet the quality standard; mining the production quality influence relationship of each process node according to the positive data and negative data, and obtaining production quality grade parameters and their influence identification relationship; constructing a quality detection sub-module for each process node based on the production quality grade parameters and their influence identification relationship; integrating the quality detection sub-modules of each process node, and setting the activation identification label of each quality detection sub-module, constructing a quality defect detection channel, and generating the adaptive quality detection module based on the quality defect detection channel, wherein the activation identification label matches the process node label.

[0036] Specifically, sorting and connecting process nodes according to the production process means arranging different process steps or links in order according to the order of the production process. Each process node represents an important link in the production process, such as coating, curing, inspection and other steps. In this process, the nodes are connected in sequence to ensure the smoothness of the production line and the validity of the data. By collecting data from each process node, positive and negative data can be obtained. Positive data refers to sample data whose production quality meets the predetermined standards, such as qualified paper tubes that meet indicators such as appearance and strength; negative data refers to sample data whose production quality does not meet the standards, such as unqualified products such as cracks and insufficient coating. These data provide the basis for subsequent quality analysis and model training.

[0037] Mining the production quality impact relationship of each process node based on positive and negative data means exploring the impact of each process node on product quality by analyzing positive and negative data. For example, too high temperature control may cause paper tube deformation, while too low temperature may cause incomplete curing and affect quality. Through statistical analysis, machine learning and other methods, the degree of influence of each node on product quality is found, thereby establishing the relationship between process nodes and production quality.

[0038] Obtaining production quality grade parameters and their impact identification relationships means clarifying the quality impact of each process node through the mining process, converting it into specific parameters, evaluating the specific impact of each process node on product quality, and finally forming a production quality rating system. These parameters can be specific values ​​such as temperature, humidity, and pressure, or indicators such as process time and coating amount. The impact identification relationship refers to how changes in parameters at each node affect the final product quality. For example, changes within a certain temperature range may directly affect the curing effect, thereby affecting the strength of the paper tube.

[0039] Constructing the quality detection submodules of each process node based on the production quality grade parameters and their impact identification relationship means establishing a special detection module for each process node to monitor and analyze the quality impact of the node in real time. For example, in the coating process, a coating amount detection submodule can be established to monitor in real time whether the coating amount meets the specified standard; in the curing process, a temperature monitoring submodule can be established to ensure that the curing temperature remains within the appropriate range. Each submodule performs quality control based on the aforementioned parameters and relationships to ensure that each node in the production process does not affect product quality.

[0040] Integrate the quality inspection submodules of each process node and set the activation identification tags of each quality inspection submodule. Building a quality defect detection channel means merging all submodules to form a complete quality inspection system. Each submodule matches the process node tag, and the activation identification tag is used to identify the activation status of the submodule. For example, when the temperature exceeds the standard, the activation tag of the temperature control submodule will be triggered. The quality defect detection channel is a detection path composed of multiple detection submodules, which can quickly identify and feedback problems through data flow, forming a quality inspection system with full monitoring.

[0041] Generating an adaptive quality inspection module based on the quality defect detection channel means integrating and optimizing all the quality inspection submodules to form an adaptive quality inspection system. Adaptability means that the system can automatically adjust the inspection strategy according to different production conditions (such as different raw materials, ambient temperature, etc.) to achieve the best quality inspection effect. In this way, the production process can be continuously optimized and the production of unqualified products can be reduced. For example, when the temperature changes greatly, the inspection module can automatically adjust the monitoring strategy of the temperature range to more accurately control the curing effect.

[0042] Through detailed analysis of each node of the production process, positive and negative data are collected, the specific impact of each node on product quality is discovered, and corresponding quality inspection sub-modules are established. Finally, by integrating these modules and setting activation identification tags, an adaptive quality inspection module is formed to monitor every link in the production process in real time, identify and handle quality defects in a timely manner, thereby optimizing the production process and improving product quality.

[0043] Furthermore, the present application also includes: dividing the production quality grades according to the quality evaluation results of chemical fiber paper tubes, the production quality grades including qualified quality grades and abnormal quality grades; dividing the positive data and negative data into samples based on the division threshold of the production quality grades, and constructing a multi-quality grade sample set; mapping all quality grade sample sets according to the node correspondence according to the process nodes, and sorting the mapped sample sets according to the process succession relationship of each process node, and constructing a process sample chain; according to the process sample chain, respectively analyzing the production quality grade parameters of each process node, and mining the correlation coefficient between each production quality grade parameter and the corresponding production quality grade, to obtain the influence identification relationship of each production quality grade parameter.

[0044] Specifically, the classification of production quality grades according to the quality evaluation results of chemical fiber paper tubes means that the quality evaluation results are divided into qualified quality grades and abnormal quality grades according to the quality evaluation of paper tubes. The qualified quality grade means that the paper tubes meet the standard requirements in various performance indicators (such as strength, appearance, size, etc.), while the abnormal quality grade means that the paper tubes have defects and do not meet the production standards, which may affect the use effect or safety. This classification helps quality control and management in the production process to ensure that the quality of each batch of products meets expectations.

[0045] Based on the threshold of production quality level, the positive data and negative data are divided into samples. Constructing a multi-quality level sample set means classifying the positive and negative data collected from the production process by quality level according to the quality level classification standard. Positive data are qualified product samples, while negative data are abnormal product samples. By setting thresholds, products can be classified into different quality levels according to their various performance indicators. A multi-quality level sample set is a collection of product data of different quality levels, which will be used for subsequent quality analysis and model training.

[0046] According to the process nodes, all quality grade sample sets are mapped according to the node correspondence, and the mapped sample sets are sorted according to the process succession relationship of each process node. Constructing a process sample chain means mapping the divided sample data with each process node in the production process. For example, samples of a certain quality grade may come from a coating node or a curing node. Through mapping, samples of different quality grades are assigned to corresponding process nodes. Then, according to the sequence of each node in the production process, these samples are arranged in the order of the process flow to construct a process sample chain. This chain describes how each process node from raw materials to finished products affects product quality.

[0047] According to the process sample chain, the production quality grade parameters of each process node are analyzed respectively, and the correlation coefficient between each production quality grade parameter and the corresponding production quality grade is mined to obtain the influence identification relationship of each production quality grade parameter. This means that after constructing the process sample chain, for each process node, the quality parameters related to it, such as temperature, humidity, pressure, time, etc., are analyzed to see how they affect the final quality grade of the product. By calculating the correlation between these parameters and the quality grade, the degree of influence of each parameter on the product quality, that is, the correlation coefficient, can be obtained, which helps identify which parameters are most critical to improving or reducing product quality.

[0048] By classifying the products into quality grades according to the quality evaluation results of chemical fiber paper tubes, collecting and classifying positive and negative data, and constructing a multi-quality grade sample set, further forming a process sample chain based on the mapping relationship of process nodes and the process succession sequence, and finally analyzing the relationship between these data and parameters, the influence of each process node in the production process on the final quality grade is revealed, and the key process parameters that affect the quality of paper tubes can be identified, thereby optimizing the production process.

[0049] Furthermore, the present application also includes: according to the process sample chain, based on the process succession relationship of each process node, aligning the level sample sets according to the production quality level, and constructing a full-cycle level sample chain; according to the full-cycle level sample chain, analyzing the collaborative influence relationship between process nodes.

[0050] Specifically, based on the existing process sample chain, the data of different process nodes are sorted and matched according to the production quality level. During the production process, each process node has a certain impact on the quality of the final product. According to the order of the process nodes, the quality grade samples of each node are aligned, that is, to ensure that each process link from raw materials to finished products of the same batch of products is consistent with its quality grade. By aligning the sample data of different nodes, a complete sample chain from beginning to end is constructed, which is called the full-cycle grade sample chain. The full-cycle grade sample chain is a complete quality control path, covering data samples of all process links from raw material preparation, processing, inspection, packaging, etc., which can fully reflect the production process of the product.

[0051] According to the full-cycle level sample chain, the synergistic influence relationship between process nodes is analyzed. By analyzing the data in the full-cycle level sample chain, the interaction between different process nodes is obtained, which in turn affects the quality of the final product. Each process node not only affects the quality of the product at its own stage, but may also produce a synergistic effect through cooperation with other nodes. For example, in the coating and curing process, the coordination relationship between the coating amount and the curing temperature may directly affect the strength and appearance of the product. By analyzing the full-cycle level sample chain, it is possible to obtain coordinated process nodes that can improve or reduce the quality of the final product.

[0052] By analyzing the data in the process sample chain, the data of each process node is aligned according to the quality level, and a full-cycle grade sample chain is constructed to ensure that each link from raw materials to finished products has corresponding quality data support. By analyzing the synergistic influence relationship between process nodes, the interaction between different nodes and their comprehensive impact on product quality are revealed, providing a basis for optimizing production processes and improving product quality.

[0053] Furthermore, the present application also includes: based on the full-cycle grade sample chain and the collaborative influence relationship, the process node is traced with the scrap quality grade as the target sample, and the influence coefficient of each process node and the scrap relationship threshold of the production quality grade parameters of the corresponding process node are identified; based on the influence coefficient of each process node and the scrap relationship threshold of the production quality grade parameters of the corresponding process node, a scrap analysis channel is constructed and added to the adaptive quality detection module.

[0054] Specifically, on the basis of the established full-cycle grade sample chain and the synergistic influence relationship between process nodes, with scrapped products as the target, trace back to each process node, and analyze the impact of each node on the quality of scrapped products. The scrap quality grade refers to those products that do not meet the quality standards at all and cannot be put into use. By tracing back to each process link, the role of each process node in the process of unqualified quality is identified. For example, excessive temperature or excessive pressure may lead to unqualified product quality. The influence coefficient refers to the degree of influence of each node on the quality of the final product. The influence coefficient can be obtained through historical data analysis, indicating the contribution of parameter changes at a certain node to the scrap rate of the product. The scrap relationship threshold refers to the parameter value of a certain process node. After reaching a certain critical point, the product quality may seriously deteriorate or be completely unqualified, resulting in scrapping. The setting of these thresholds helps to identify which process links need special attention and optimization.

[0055] After identifying the influence coefficient and scrap relationship threshold of each process node, a special scrap analysis channel is constructed and added to the adaptive quality inspection module. The function of the scrap analysis channel is to monitor the parameters of each process node in real time to determine whether it is close to or exceeds the scrap relationship threshold. When it is detected that the parameters of a process node are close to the scrap threshold, the channel will trigger an alarm and take corresponding corrective measures, such as adjusting process parameters or stopping production for inspection. The adaptive quality inspection module refers to a system that can automatically adjust the inspection strategy according to real-time data. It can dynamically adjust the quality inspection parameters to adapt to various changes in the production process, thereby ensuring production quality.

[0056] By analyzing the synergistic influence relationship between the full-cycle grade sample chain and the process nodes, taking the scrap quality level as the goal, tracing the influence coefficient of each process node, and determining the scrap relationship threshold of each node, a scrap analysis channel is finally constructed and integrated into the adaptive quality detection module. The scrap analysis channel can detect the key process nodes in the production process in real time, and promptly identify the links that may lead to product scrapping, thereby providing data support for the optimization of the production process.

[0057] Furthermore, the present application also includes: based on the full-cycle grade sample chain and collaborative influence relationship, the process node threshold is traced with the qualified quality grade as the target sample to identify the qualified threshold of each process node; according to the qualified threshold and scrap relationship threshold of each process node, the optimization parameter interval is set; based on the full-cycle grade sample chain and collaborative influence relationship, a timing cumulative optimization space is established, and the timing cumulative optimization space has an evaluation function with the goal of maximizing the qualified quality grade, wherein the optimization parameter interval is used as an input constraint, and the process flow timing optimization search is performed according to the process nodes located by the input constraints through the timing cumulative optimization space, and the post-process nodes are evaluated for cumulative quality targets to obtain the process node parameter strategy with the highest evaluation result quality grade, and the process node parameter strategy is used to perform post-process node reprocessing identification and control; based on the timing cumulative optimization space, a reprocessing optimization analysis sub-channel is established and added to the adaptive quality detection module.

[0058] Specifically, based on the existing full-cycle grade sample chain and synergistic influence relationship, select products with qualified quality grades as the target, trace back to each process node, and analyze the impact of each process node on the final product quality meeting the qualified standards. The qualified quality grade means that the product meets the production quality standards and meets the expected performance requirements. Each process node, such as temperature, pressure, coating amount, etc., has a specific threshold, which indicates the parameter value that must be maintained at the node to achieve qualified quality. By tracing the qualified thresholds of these nodes, it is possible to determine which process nodes are critical to qualified quality, thereby optimizing the production process.

[0059] According to the qualified threshold and scrap relationship threshold of each process node, setting the optimization parameter interval means determining a suitable optimization parameter interval after identifying the qualified threshold and scrap relationship threshold of each process node. The optimization parameter interval refers to the range within which the parameters of each process node (such as temperature, humidity, time, etc.) should be in the production process to ensure that the quality of the product meets the qualified standards while avoiding excessive deviation from the scrap threshold. The setting of this interval allows the production process to find a balance between qualified quality and scrap, improving production efficiency while reducing resource waste.

[0060] Based on the full-cycle grade sample chain and the synergistic influence relationship, a time series cumulative optimization space is established. The time series cumulative optimization space has an evaluation function with the goal of maximizing the qualified quality level, which means that the time series cumulative optimization space is constructed on the basis of the existing full-cycle grade sample chain and the synergistic influence relationship between the process nodes. Such as the long short time series model (LSTM) and the Markov chain. LSTM can process and predict long-time span dependencies, while the Markov chain can predict the transfer of the next state based on the current state. The time series model can predict how to adjust the strategy of the subsequent nodes in the current state, so as to finally meet the qualified requirements. For example, based on the current state (such as the parameters of process node A), the time series model can analyze how to adjust the parameters of the subsequent nodes (such as nodes B, C, etc.) to ensure that the overall process reaches the optimal state at a certain point in the future, so as to obtain qualified product quality. Through time series optimization, the entire production process can be dynamically adjusted according to the constantly changing process parameters, so as to maximize the product quality, adjust the parameters of each process node, and make the final production quality meet the qualified standards. The evaluation function is used to measure the impact of adjustment strategies at different process nodes on the quality of the final product. The goal is to maximize the qualified quality level, that is, to make the final product quality as optimal or as compliant as possible.

[0061] Among them, by defining the optimization parameter interval of each process node, the parameter range is used as an input constraint to limit the adjustable parameter values ​​during the optimization process. The optimization parameters may include temperature, humidity, pressure, time, etc. The timing cumulative optimization space is used to perform timing optimization search of the process flow to determine the adjustment strategy for each process node at the appropriate time point. The goal of the optimization search is to find an adjustment path so that the parameters of each node meet the optimal quality requirements and the overall quality can be further improved through the adjustment of subsequent nodes.

[0062] Cumulative quality target evaluation of post-process nodes means that in the process of timing optimization, in addition to analyzing the single impact of each process node, the quality impact of subsequent nodes must also be comprehensively considered. Post-process nodes refer to the subsequent steps after adjustments to the previous nodes, such as curing after coating, inspection after processing, etc. Cumulative quality target evaluation is a comprehensive evaluation of the final quality of all process nodes after timing optimization, to obtain the process node parameter strategy with the highest quality level of the evaluation result. These parameter combinations can maximize the quality level of the final product to ensure that each step has a positive effect on the quality of qualified products.

[0063] Using the process node parameter strategy to perform post-process node reprocessing identification control means that after obtaining the optimal process node parameter strategy, it is applied to the subsequent production links. If some process nodes fail to meet the expected quality standards during the production process, they are automatically adjusted according to the optimized parameter strategy, and the reprocessing process may be initiated. Through real-time analysis and control strategies, problems in the production process are dynamically adjusted to ensure that the final product meets the quality standards.

[0064] Based on the time series cumulative optimization space, a reprocessing optimization analysis sub-channel is established. Adding it to the adaptive quality inspection module means creating an optimization analysis sub-channel specifically for reprocessing based on the time series cumulative optimization space and adding it to the adaptive quality inspection module. The function of the reprocessing optimization analysis sub-channel is to monitor the products that may need to be reprocessed in the production process in real time, and analyze the process nodes that need to be adjusted or reprocessed if they do not meet the standards. Each node in the production process can be monitored and optimized to ensure that even if problems occur, reprocessing can be carried out in a timely manner, and the final product meets the quality requirements.

[0065] By constructing a full-cycle grade sample chain and collaborative influence relationship, tracing the process node threshold of the qualified quality grade, identifying the qualified and scrapped relationship threshold of each node, and setting an optimization parameter range. Based on these parameter intervals, a time-series cumulative optimization space is established, and through the process flow timing optimization search, the process node parameter strategy that can maximize the qualified quality is found, and these strategies are applied to subsequent production. Finally, a reprocessing optimization analysis sub-channel is created to ensure that any unqualified products can be reprocessed in time and improve quality.

[0066] Furthermore, the present application also includes: integrating the quality defect detection channel, the scrap analysis channel, and the reprocessing optimization analysis sub-channel to construct the adaptive quality detection module; constructing a test sample set based on real-time monitoring data, using the test sample set to test and verify the adaptive quality detection module, obtaining verification results, and performing feedback incremental learning based on the loss value of the verification results.

[0067] Specifically, integrating the quality defect detection channel, scrap analysis channel, and reprocessing optimization analysis sub-channel to build an adaptive quality inspection module means combining multiple different analysis channels (such as quality defect detection, scrap analysis, and reprocessing optimization analysis) to form a unified adaptive quality inspection module. These analysis channels are responsible for different tasks. The quality defect detection channel is used to monitor product defects in the production process, the scrap analysis channel is used to analyze which products should be scrapped, and the reprocessing optimization analysis sub-channel is used to identify which products need to be reprocessed. By integrating these channels into one module, the strategy can be flexibly adjusted according to different situations during the production process to achieve automated and efficient quality control. The adaptive quality inspection module can automatically adjust its working strategy based on real-time data and feedback to achieve the best quality control effect.

[0068] Building a test sample set based on real-time monitoring data means using real-time data collected by sensors and other equipment during the production process to build a test sample set. Real-time monitoring data may include multiple parameters such as temperature, humidity, pressure, speed, etc. These data can reflect every detail of the production process in real time. The purpose of building a test sample set is to use these data for analysis and verification to ensure the accuracy and effectiveness of the quality inspection module.

[0069] Testing and verifying the adaptive quality inspection module using a test sample set means inputting the previously constructed test sample set into the adaptive quality inspection module for testing. Through verification, it can be checked whether the quality inspection module can correctly identify product quality defects, predict scrapped products, and optimize the reprocessing process. The test verification process is equivalent to simulating the production environment to ensure that the inspection module can operate effectively in the actual production process.

[0070] Feedback incremental learning based on the loss value of the verification result means calculating the loss value through the verification result obtained by the test. The loss value refers to the difference between the actual result and the predicted result. The smaller the loss, the higher the accuracy of the model. Incremental learning based on the loss value means continuously adjusting and optimizing the model based on feedback to make it better suited to the quality inspection tasks in the production process. Incremental learning can continuously improve the accuracy of the model, thereby continuously optimizing the production quality inspection process.

[0071] By integrating multiple quality analysis channels (quality defect detection, scrap analysis, and reprocessing optimization analysis) into an adaptive quality inspection module, flexible and efficient quality control can be achieved. Test sample sets are built through real-time monitoring data, and the quality inspection module is verified through these samples. Feedback incremental learning is performed based on the loss value of the verification result, so that the inspection module can be continuously optimized to improve its accuracy and adaptability, which not only improves the accuracy of quality control, but also enables the system to be optimized in a dynamic environment through the adaptive learning mechanism.

[0072] To sum up, the chemical fiber paper tube production quality inspection method provided by the present application has the following technical effects: obtaining real-time monitoring data of the production line by connecting the data acquisition module, the data acquisition module is connected to the sensor arranged on the production line, and is used for real-time synchronization of sensor data; the real-time monitoring data is integrated and stored according to the monitoring location, data source, and monitoring time, and a production database is constructed. The monitoring data in the production database is pre-processed to establish a process data block, and the process data block has a process node label; the production quality grade parameters are analyzed according to the production process, and an adaptive quality inspection module is constructed. The adaptive quality inspection module includes multiple process cycle channels, and each process cycle is passed The channel includes quality defect detection, scrap analysis, and reprocessing optimization analysis sub-channels; data is extracted according to the process data block and imported into the adaptive quality detection module, and matching analysis is performed through the multiple process cycle channels to obtain quality detection results, which are used to locate the process according to the process node label, and send corresponding processing guidance or product scrap processing feedback according to the quality detection result based on the process positioning. In other words, by realizing the technical goal of intelligent quality detection based on real-time data collection and analysis, through dynamic monitoring and adaptive adjustment of multiple nodes and multiple factors, the technical effect of improving production efficiency, reducing resource waste, and ensuring stable product quality and traceability is achieved.

[0073] Embodiment 2: Based on the same invention concept as the chemical fiber paper tube production quality detection method in the previous embodiment, this application also provides a chemical fiber paper tube production quality detection system, please refer to the attached Figure 2, including: a data acquisition module 11, the data acquisition module 11 is used to connect the data acquisition module to obtain real-time monitoring data of the production line, the data acquisition module is connected to the sensors arranged on the production line, and is used for real-time synchronization of sensor data; an integrated storage module 12, the integrated storage module 12 is used to integrate and store the real-time monitoring data according to the monitoring location, data source, and monitoring time, build a production database, pre-process the monitoring data in the production database, and establish a process data block, the process data block has a process node label; a parameter parsing module 13, the parameter parsing module 13 is used to perform production quality grade parameter parsing according to the production process, and build an adaptive quality detection module, the adaptive quality detection module includes multiple process cycle channels, each process cycle channel includes quality defect detection and scrap analysis, and reprocessing optimization analysis sub-channels; a matching analysis module 14, the matching analysis module 14 is used to extract data according to the process data block and import it into the adaptive quality detection module, perform matching analysis through the multiple process cycle channels, and obtain quality detection results, the quality detection results are used to perform process positioning according to the process node label, and send corresponding processing guidance or product scrap processing feedback according to the quality detection result based on the process positioning.

[0074] Furthermore, the chemical fiber paper tube production quality inspection system is also used to: analyze the production process of chemical fiber paper tube production, configure sensors in each process based on the influence of process parameters on process quality, and the sensor equipment includes temperature sensors, bonding sensors, and industrial cameras; locate the sensors to set process nodes and layout positions, and establish a data connection relationship between data source and process positioning; and construct the data acquisition module based on the data connection relationship between data source and process positioning.

[0075] Furthermore, the chemical fiber paper tube production quality inspection system is also used to: sort and connect process nodes according to the production process, collect positive data and negative data of each process node, the positive data is sample data whose production quality finally meets the quality standard, and the negative data is sample data whose production quality does not meet the quality standard; mine the production quality influence relationship of each process node according to the positive data and negative data, and obtain production quality grade parameters and their influence identification relationship; construct a quality inspection sub-module for each process node based on the production quality grade parameters and their influence identification relationship; integrate the quality inspection sub-modules of each process node, set the activation identification label of each quality inspection sub-module, construct a quality defect detection channel, and generate the adaptive quality inspection module based on the quality defect detection channel, wherein the activation identification label matches the process node label.

[0076] Furthermore, the chemical fiber paper tube production quality inspection system is also used to: divide the production quality grades according to the quality evaluation results of the chemical fiber paper tubes, the production quality grades including qualified quality grades and abnormal quality grades; divide the positive data and negative data into samples based on the division threshold of the production quality grades, and construct a multi-quality grade sample set; map all quality grade sample sets according to the node correspondence according to the process nodes, and sort the mapped sample sets according to the process succession relationship of each process node to construct a process sample chain; according to the process sample chain, analyze the production quality grade parameters of each process node respectively, and mine the correlation coefficient between each production quality grade parameter and the corresponding production quality grade to obtain the influence identification relationship of each production quality grade parameter.

[0077] Furthermore, the chemical fiber paper tube production quality inspection system is also used to: align the grade sample sets according to the production quality grade based on the process succession relationship of each process node according to the process sample chain, and construct a full-cycle grade sample chain; and analyze the synergistic influence relationship between process nodes according to the full-cycle grade sample chain.

[0078] Furthermore, the chemical fiber paper tube production quality inspection system is also used to: based on the full-cycle grade sample chain and the collaborative influence relationship, trace the process nodes with the scrap quality grade as the target sample, identify the influence coefficient of each process node, and the scrap relationship threshold of the production quality grade parameters of the corresponding process nodes; based on the influence coefficient of each process node and the scrap relationship threshold of the production quality grade parameters of the corresponding process nodes, construct a scrap analysis channel and add it to the adaptive quality inspection module.

[0079] Furthermore, the chemical fiber paper tube production quality inspection system is also used for: based on the full-cycle grade sample chain and collaborative influence relationship, tracing the process node threshold with the qualified quality grade as the target sample, and identifying the qualified threshold of each process node; setting the optimization parameter interval according to the qualified threshold and scrap relationship threshold of each process node; establishing a time series cumulative optimization space based on the full-cycle grade sample chain and collaborative influence relationship, and the time series cumulative optimization space has an evaluation function with the goal of maximizing the qualified quality grade, wherein the optimization parameter interval is used as an input constraint, and the process flow timing optimization search is performed on the process nodes located according to the input constraints through the time series cumulative optimization space, and the post-process nodes are evaluated by cumulative quality targets to obtain the process node parameter strategy with the largest evaluation result quality grade, and the process node parameter strategy is used to perform post-process node reprocessing identification and control; based on the time series cumulative optimization space, a reprocessing optimization analysis sub-channel is established and added to the adaptive quality inspection module.

[0080] Furthermore, the chemical fiber paper tube production quality inspection system is also used to: integrate the quality defect detection channel, scrap analysis channel, and reprocessing optimization analysis sub-channel to construct the adaptive quality inspection module; construct a test sample set based on real-time monitoring data, use the test sample set to test and verify the adaptive quality inspection module, obtain verification results, and perform feedback incremental learning based on the loss value of the verification results.

[0081] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The chemical fiber paper tube production quality inspection method and specific examples in the aforementioned embodiment one are also applicable to the chemical fiber paper tube production quality inspection system of this embodiment. Through the aforementioned detailed description of the chemical fiber paper tube production quality inspection method, technical personnel in this field can clearly understand the chemical fiber paper tube production quality inspection system of this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0082] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0083] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A method for detecting the production quality of chemical fiber paper tubes, characterized in that: include: Connecting to the data acquisition module to obtain real-time monitoring data of the production line, the data acquisition module is connected to the sensors arranged on the production line for real-time synchronization of sensor data; Integrate and store the real-time monitoring data according to monitoring location, data source, and monitoring time, build a production database, pre-process the monitoring data in the production database, and establish a process data block, wherein the process data block has a process node label; Analyze the production quality level parameters according to the production process and build an adaptive quality detection module, which includes multiple process cycle channels, each of which includes quality defect detection, scrap analysis, and reprocessing optimization analysis sub-channels; Data is extracted according to the process data block and imported into the adaptive quality inspection module. Matching analysis is performed through the multiple process cycle channels to obtain quality inspection results. The quality inspection results are used to locate the process according to the process node labels, and corresponding processing instructions or product scrapping feedback are sent according to the quality inspection results based on the process positioning.

2. The chemical fiber paper tube production quality detection method according to claim 1, characterized in that: Connect the data acquisition module to obtain real-time monitoring data of the production line, which previously included: Analyze the production process of chemical fiber paper tube production, configure sensors in each process based on the influence of process parameters on process quality, and the sensor equipment includes temperature sensors, bonding sensors, and industrial cameras; Locate the sensor to set the process node and layout position, and establish a data connection relationship between the data source and the process positioning; The data acquisition module is constructed based on the data connection relationship between the data source and the process positioning.

3. The chemical fiber paper tube production quality detection method according to claim 1, characterized in that: The production quality grade parameter analysis is performed according to the production process to construct an adaptive quality detection module, including: Sort and connect the process nodes according to the production process, and collect positive data and negative data of each process node, wherein the positive data is sample data whose production quality finally meets the quality standard, and the negative data is sample data whose production quality does not meet the quality standard; Mining the production quality impact relationship of each process node according to the positive data and the negative data to obtain the production quality grade parameters and their impact identification relationship; Based on the production quality grade parameters and their impact identification relationships, quality detection submodules for each process node are respectively constructed; The quality detection submodules of each process node are integrated, and the activation identification tag of each quality detection submodule is set to construct a quality defect detection channel, and the adaptive quality detection module is generated based on the quality defect detection channel, wherein the activation identification tag matches the process node tag.

4. The chemical fiber paper tube production quality detection method according to claim 3, characterized in that: The production quality influence relationship of each process node is mined according to the positive data and the negative data to obtain the production quality grade parameters and their influence identification relationship, including: The production quality grades are divided according to the quality evaluation results of chemical fiber paper tubes, and the production quality grades include qualified quality grades and abnormal quality grades; Based on the division threshold of the production quality level, the positive data and the negative data are divided into samples to construct a multi-quality level sample set; According to the process nodes, all quality level sample sets are mapped according to the node correspondence, and according to the process connection relationship of each process node, the mapped sample sets are sorted by process to construct a process sample chain; According to the process sample chain, the production quality grade parameters of each process node are analyzed respectively, and the correlation coefficient between each production quality grade parameter and the corresponding production quality grade is mined to obtain the influence identification relationship of each production quality grade parameter.

5. The method for detecting the production quality of chemical fiber paper tubes according to claim 4, characterized in that: Also includes: According to the process sample chain, based on the process succession relationship of each process node, the grade sample set is aligned according to the production quality grade to build a full-cycle grade sample chain; According to the full-cycle level sample chain, the synergistic impact relationship between process nodes is analyzed.

6. The method for detecting the production quality of chemical fiber paper tubes according to claim 5, characterized in that: Building an adaptive quality detection module also includes: Based on the full-cycle grade sample chain and the collaborative influence relationship, the process node is traced with the scrapped quality grade as the target sample to identify the influence coefficient of each process node and the scrapped relationship threshold of the production quality grade parameter of the corresponding process node; Based on the influence coefficient of each process node and the scrap relationship threshold of the production quality grade parameter of the corresponding process node, a scrap analysis channel is constructed and added to the adaptive quality detection module.

7. The method for detecting the production quality of chemical fiber paper tubes according to claim 6, characterized in that: Building an adaptive quality detection module also includes: Based on the full-cycle grade sample chain and the synergistic influence relationship, the qualified quality grade is used as the target sample to trace the process node threshold and identify the qualified threshold of each process node; According to the qualified threshold and the scrapped relationship threshold of each process node, an optimization parameter interval is set; Based on the full-cycle grade sample chain and the collaborative influence relationship, a time-series cumulative optimization space is established, and the time-series cumulative optimization space has an evaluation function with the goal of maximizing the qualified quality grade, wherein the optimization parameter interval is used as an input constraint, and the process flow timing optimization search is performed according to the process node located by the input constraint through the time-series cumulative optimization space, and the cumulative quality target evaluation is performed on the post-process nodes to obtain the process node parameter strategy with the maximum evaluation result quality grade, and the post-process node reprocessing identification control is performed using the process node parameter strategy; Based on the time series cumulative optimization space, a reprocessing optimization analysis sub-channel is established and added to the adaptive quality detection module.

8. The method for detecting the production quality of chemical fiber paper tubes according to claim 7, characterized in that: Also includes: Integrate the quality defect detection channel, the scrap analysis channel, and the reprocessing optimization analysis sub-channel to construct the adaptive quality detection module; A test sample set is constructed based on real-time monitoring data, the adaptive quality detection module is tested and verified using the test sample set to obtain a verification result, and feedback incremental learning is performed according to the loss value of the verification result.

9. Chemical fiber paper tube production quality inspection system, characterized by: The steps for implementing the chemical fiber paper tube production quality inspection method according to any one of claims 1 to 8 include: A data acquisition module, which is used to connect to a data acquisition module to obtain real-time monitoring data of the production line. The data acquisition module is connected to sensors arranged on the production line for real-time synchronization of sensor data; An integrated storage module, the integrated storage module is used to integrate and store the real-time monitoring data according to monitoring location, data source, and monitoring time, build a production database, pre-process the monitoring data in the production database, and establish a process data block, wherein the process data block has a process node label; A parameter analysis module, which is used to analyze production quality grade parameters according to the production process and construct an adaptive quality detection module. The adaptive quality detection module includes multiple process cycle channels, each of which includes quality defect detection, scrap analysis, and reprocessing optimization analysis sub-channels; A matching analysis module, wherein the matching analysis module is used to extract data according to the process data block and import it into the adaptive quality inspection module, perform matching analysis through the multiple process cycle channels, and obtain quality inspection results. The quality inspection results are used to locate the process according to the process node label, and send corresponding processing instructions or product scrapping feedback according to the quality inspection results based on the process positioning.

Images