Disposable underpants manufacturing management system based on production equipment state analysis

Abstract

The application discloses a disposable underpants manufacturing management system based on production equipment state analysis, relates to the technical field of manufacturing management, and solves the problem of insufficient real-time performance caused by network transmission delay in the prior art, i.e., a data acquisition module, which acquires yield, abnormal information, efficiency, downtime length, temperature, pressure, conveying speed and visual data in real time; a state analysis module, which analyzes the equipment state through machine learning and calculates the health degree; a dynamic control module, which adjusts the operation parameters according to the health degree; and a quality correlation database, which stores the mapping relationship between the equipment state and the quality index and triggers quality traceability.

Description

Technical Field

[0001] This invention relates to the field of manufacturing management technology, specifically to a disposable underwear manufacturing management system based on production equipment status analysis. Background Technology

[0002] This intelligent management platform utilizes IoT, big data analytics, and AI technologies to monitor the operational status of production equipment in real time, provide fault warnings, and optimize performance. The system focuses on the characteristics of disposable underwear production scenarios, such as high-load equipment operation, sensitive process parameters, and strong demand for quality traceability, to achieve full-chain digital control from equipment health management to production efficiency improvement.

[0003] However, in existing technologies, traditional methods using single-point threshold alarms cannot reflect the overall health status of equipment, and existing systems usually shut down for maintenance directly after detecting anomalies; at the same time, traditional equipment monitoring systems usually adopt a centralized data processing architecture, which suffers from insufficient real-time performance due to network transmission delays, and conventional anomaly detection algorithms often ignore the periodic characteristics of operating conditions when processing periodic signals, leading to an increased false alarm rate.

[0004] To address the aforementioned technical shortcomings, a solution is proposed. Summary of the Invention

[0005] The purpose of this invention is to solve the problems mentioned above by proposing a disposable underwear manufacturing management system based on production equipment status analysis.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] A disposable underwear manufacturing management system based on production equipment status analysis includes a management center, which is connected to:

[0008] The data acquisition module acquires real-time data on output, anomalies, efficiency, downtime, temperature, pressure, conveying speed, and visual data.

[0009] The status analysis module uses machine learning to analyze the device status and calculate its health.

[0010] The dynamic control module adjusts operating parameters based on the health status.

[0011] A quality-related database stores the mapping relationship between device status and quality indicators, triggering quality traceability.

[0012] In a preferred embodiment of the present invention, the data acquisition module is a multi-source sensor network deployed on the production line, which acquires data through distributed sensors.

[0013] In a preferred embodiment of the present invention, the operating parameters of the production line equipment are transmitted to the edge computing node in real time through a distributed sensor network; the temperature sensor monitors the surface temperature distribution of the hot press plate, the pressure sensor records the closed pressure curve of the molding die, and the image acquisition device captures the flatness characteristics of the material conveying; after normalization, the collected data are input into a convolutional neural network to extract the feature vector of the equipment operating status.

[0014] In a preferred embodiment of the present invention, the state analysis module includes a combined architecture of an edge computing unit, a cloud analysis unit, and an anomaly detection algorithm; the edge computing unit refers to a data processing unit deployed at the network edge that is physically close to the production equipment; the cloud analysis unit refers to a time-series data analysis module deployed on a remote server; and the anomaly detection algorithm refers to a composite algorithm that integrates unsupervised learning and dynamic data analysis.

[0015] In a preferred embodiment of the present invention, the edge computing unit first performs noise reduction processing on temperature, pressure, and vibration signals to form lightweight feature vectors that are uploaded to the cloud. After receiving the feature vectors, the cloud analysis unit analyzes the changing trends of equipment parameters through a pre-trained LSTM network and calculates the probability distribution of remaining service life. The anomaly detection algorithm simultaneously performs spectral slicing on the periodic vibration signal, uses a sliding window to divide the working cycle, and constructs an isolated tree model in each window to identify spectral distortion features. The collaborative work of the three components enables multi-dimensional evaluation of the equipment status.

[0016] In a preferred embodiment of the present invention, the operation process of the dynamic control module is as follows:

[0017] In the sealing process, continuous temperature monitoring data triggers the PID controller to output a compensation signal, while the transmission mechanism executes a speed reduction command to form a dual regulation mechanism, avoiding insufficient sealing strength due to temperature overshoot. When the health of the slitting equipment decreases, the control system automatically switches to the standby blade and generates a maintenance task to prevent blade failure from causing a decrease in material cutting accuracy. By collecting production data in real time, the raw material supply system dynamically matches the consumption rate to ensure that the production rhythm and material supply remain synchronized, preventing raw material accumulation or shortage.

[0018] In a preferred embodiment of the present invention, the quality association database is used as follows:

[0019] The correlation model between equipment vibration amplitude and joint fracture strength establishes a negative correlation between vibration amplitude and joint strength by collecting vibration sensor data in real time and combining it with destructive tensile test results. When the vibration amplitude exceeds the threshold, equipment vibration reduction measures are automatically triggered. The quantitative relationship table between temperature and humidity parameters of the sterilization process and microbial residue is based on the results of microbial culture experiments under different temperature and humidity combinations, forming a visual comparison standard for sterilization effect. When abnormal microbial residue is detected, the temperature and humidity control deviation of the sterilization equipment can be traced back. The regression analysis function of the wear degree of slitting tool on material loss rate establishes a quadratic function relationship by periodically measuring the wear of the tool edge and combining it with the weighing data of raw material scraps. When the function prediction value exceeds the upper limit of material loss, a tool replacement instruction is generated.

[0020] In a preferred embodiment of the present invention, after the data acquisition module completes data acquisition, it performs status analysis on the production equipment and uses the production output as a status evaluation parameter for the production equipment. If the status evaluation parameter is within a set threshold range, the production equipment is set to a normal state, and the IoT module continues production according to the current production line operation settings. Conversely, if the status evaluation parameter is not within the set threshold range, the production equipment is set to an abnormal state, the IoT module adjusts the current production line operation settings, and marks the current output and production rate as abnormal information. After the abnormal information is marked, the production line capacity is detected, and the range of production line capacity decrease during the production line adjustment and increase phases is collected. The production capacity is evaluated using the ratio of the current production cycle's production rate to the set workload's production rate. If the production line's capacity decreases by less than the set threshold, the production line's capacity is considered acceptable; conversely, if the production line's capacity decreases by more than the set threshold, the production line's capacity is considered unacceptable. The IoT module analyzes the distribution of downtime on the production line equipment. If the downtime distribution is irregular, there is a fluctuation in the equipment's operating cycle. The IoT module then resets the equipment's operating cycle. If the downtime distribution is regular, it is inferred that abnormal information on the production line is affecting its operation. In other words, after the IoT module completes the production line adjustment, it predicts abnormal information in advance and makes prior adjustments to the production line after the prediction.

[0021] Compared with the prior art, the beneficial effects of the present invention are:

[0022] 1. This application provides timely warnings when equipment performance deteriorates slightly, preventing batch defects caused by equipment malfunctions. It maintains production process stability through dynamic parameter adjustments, reducing capacity losses due to unplanned downtime. By establishing a correlation model between equipment status and quality data, it significantly shortens the root cause analysis time for quality anomalies. It achieves closed-loop management throughout the entire process, from equipment monitoring to quality control, improving the yield rate of disposable underwear production.

[0023] 2. This application achieves millisecond-level response speed for production equipment status analysis, solving the latency problem of traditional cloud processing architecture; it accurately predicts the remaining service life of equipment through deep learning models, providing data support for maintenance plan formulation; and it adopts a composite anomaly detection mechanism, which effectively improves the accuracy of fault identification of periodic production equipment, providing reliable status monitoring assurance for manufacturing process quality control. Attached Figure Description

[0024] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0025] Figure 1 This is a schematic diagram of the system of the present invention;

[0026] Figure 2 This is a flowchart of the method in Embodiment 2 of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0029] In existing technologies, the production process of disposable underwear commonly suffers from a disconnect between equipment status monitoring and quality control. Traditional methods rely primarily on manual inspections and offline quality sampling, making it difficult to detect the correlation between equipment anomalies and product defects in real time. Existing monitoring systems typically use single sensors for threshold alarms, failing to comprehensively analyze multi-dimensional equipment data and lacking dynamic control mechanisms based on equipment health status. When the temperature of the hot-sealing machine drifts or the slitting blades wear out, it is often only discovered after a batch of defective products has been produced, resulting in material waste and rework costs.

[0030] To address these issues, researchers discovered a non-linear correlation between equipment status and product quality, necessitating the establishment of a multi-parameter fusion monitoring system. Long-term observation of key processes on the production line, such as sterilization, hot pressing, and slitting, revealed that changes in vibration spectrum occurred earlier than visible product defects. This led to the idea of ​​building an equipment health assessment model, using machine learning algorithms to map sensor data to equipment status levels. Further, it was realized that a dynamic compensation mechanism was needed to automatically adjust process parameters in the early stages of equipment performance degradation, rather than passively shutting down for maintenance. Ultimately, a closed-loop management approach was formed, encompassing data acquisition, status analysis, and dynamic control.

[0031] Therefore, please refer to Figure 1 As shown, this application proposes a disposable underwear manufacturing management system based on production equipment status analysis, including a management center, which is connected to a data acquisition module, a status analysis module, a dynamic control module, and a quality correlation database.

[0032] The data acquisition module acquires real-time data on output, anomalies, efficiency, downtime, temperature, pressure, conveying speed, and visual data.

[0033] The status analysis module uses machine learning to analyze the device status and calculate its health.

[0034] The dynamic control module adjusts operating parameters based on the health status;

[0035] The quality-related database stores the mapping relationship between device status and quality indicators, triggering quality traceability.

[0036] The data acquisition module refers to the multi-source sensor network deployed on the production line. Specifically, it can be implemented using distributed sensor nodes connected by an RS485 bus to synchronously acquire equipment physical parameters and visual data.

[0037] The state analysis module refers to a computing unit with time-series data processing capabilities. Specifically, it can be implemented using an edge computing device equipped with the TensorFlow Lite framework, which identifies abnormal device patterns through a trained classification model.

[0038] The dynamic control module refers to a controller with real-time feedback adjustment function. Specifically, it can be implemented by a PLC and frequency converter linkage system to optimize process parameters based on the health assessment results.

[0039] A quality correlation database refers to a dataset that stores the correlation between equipment operating conditions and product quality inspection results. Specifically, it can be implemented using a hybrid architecture of time-series databases and relational databases to establish the correspondence between equipment abnormal events and quality defects.

[0040] Specifically, the operating parameters of the production line equipment are transmitted to the edge computing nodes in real time through a distributed sensor network; temperature sensors monitor the temperature distribution on the surface of the hot press plate, pressure sensors record the closed pressure curve of the molding die, and image acquisition devices capture the flatness characteristics of the material conveying; the distributed sensor network refers to a monitoring system composed of various types of sensors deployed at different physical locations on the production line, which can be implemented by combining temperature sensors, pressure sensors, and vibration sensors, and can simultaneously collect multi-dimensional parameters of equipment operation.

[0041] After being normalized, this multidimensional data is input into a convolutional neural network to extract feature vectors of the device's operating status.

[0042] The status analysis module calculates the current device's health index by comparing it with historical health status data, and triggers an alert when the index falls below a preset threshold.

[0043] After receiving a signal indicating a decrease in health status, the dynamic control module automatically adjusts the equipment's operating parameters, such as compensating for hot pressing temperature deviations or switching to a backup slitting tool.

[0044] The quality-related database continuously records changes in equipment status and product sampling results. When an abnormality in a specific equipment parameter is detected, the system automatically traces the production batch within that period and performs a quality review.

[0045] Compared to existing technologies, traditional methods using single-point threshold alarms cannot reflect the overall health status of equipment. This solution achieves accurate equipment status assessment through multi-dimensional data fusion and machine learning models. Existing systems typically shut down for maintenance immediately upon detecting anomalies, while this solution maintains production continuity through dynamic parameter adjustments. Conventional quality management systems operate independently of equipment monitoring systems, but this solution establishes a mapping relationship between equipment status and quality indicators, enabling rapid quality traceability for abnormal operating conditions.

[0046] Through the above technical solutions, this application can provide timely warnings when equipment performance deteriorates slightly, avoiding batch defects caused by equipment malfunctions. Dynamic parameter adjustments maintain production process stability, reducing capacity losses due to unplanned downtime. Establishing a correlation model between equipment status and quality data significantly shortens the root cause analysis time for quality anomalies. It achieves closed-loop management throughout the entire process, from equipment monitoring to quality control, improving the yield rate of disposable underwear production.

[0047] Example 2

[0048] Please see Figure 2 As shown, this application further proposes a specific implementation of the state analysis module, including a combined architecture of an edge computing unit, a cloud analysis unit, and an anomaly detection algorithm.

[0049] The edge computing unit refers to a data processing unit deployed at the network edge, physically close to the production equipment. Specifically, it can be implemented using an embedded industrial computer in conjunction with data cleaning algorithms. This involves compressing the characteristics of the equipment's vibration signals by calculating their time-domain statistics and frequency-domain energy distribution. The purpose of this unit is to reduce the amount of raw data transmitted, ensuring the real-time nature of the condition analysis.

[0050] The cloud-based analytics unit refers to a time-series data analysis module deployed on a remote server. Specifically, it can be implemented using a bidirectional LSTM neural network built on the TensorFlow framework. This model is established by analyzing the time-series trends of device operating parameters. The purpose of this unit is to utilize cloud computing resources to process complex models and achieve accurate lifetime prediction.

[0051] Among them, the anomaly detection algorithm refers to a composite algorithm that integrates unsupervised learning and dynamic data analysis. Specifically, it can use a sliding window mechanism to divide the equipment operation cycle, and apply the isolated forest algorithm to detect outliers in spectral features within each window. The purpose of this algorithm is to adapt to the periodic operating characteristics of production equipment and improve the accuracy of anomaly pattern recognition.

[0052] Specifically, the edge computing unit first performs noise reduction processing on temperature, pressure, and vibration signals, extracts feature parameters such as peak factor and kurtosis coefficient, and forms a lightweight feature vector that is then uploaded to the cloud.

[0053] After receiving the feature vector, the cloud-based analysis unit analyzes the changing trends of device parameters through a pre-trained LSTM network and calculates the probability distribution of the remaining lifespan.

[0054] The anomaly detection algorithm simultaneously slices the spectrum of the periodic vibration signal, uses a sliding window to divide the working period, and builds an isolated tree model in each window to identify spectral distortion features.

[0055] The collaborative work of the three components enables multi-dimensional assessment of the device's status.

[0056] Compared to existing technologies, traditional equipment monitoring systems typically employ a centralized data processing architecture, resulting in insufficient real-time performance due to network transmission latency. Existing lifespan prediction methods largely rely on empirical formulas, making it difficult to capture the nonlinear characteristics of equipment degradation. Conventional anomaly detection algorithms often ignore the cyclical nature of operating conditions when processing periodic signals, leading to increased false alarm rates. This solution utilizes a collaborative architecture of edge computing and cloud computing to reduce response latency while maintaining computational accuracy; it employs an LSTM network to establish an equipment degradation model, effectively learning complex temporal features; and it combines an anomaly detection method with a sliding window mechanism, significantly improving the accuracy of identification under periodic operating conditions.

[0057] Through the above technical solutions, this application achieves millisecond-level response speed for production equipment status analysis, solving the latency problem of traditional cloud processing architecture; it accurately predicts the remaining service life of equipment through deep learning models, providing data support for maintenance plan formulation; and it adopts a composite anomaly detection mechanism, which effectively improves the accuracy of fault identification of periodic production equipment, providing reliable status monitoring guarantee for manufacturing process quality control.

[0058] Example 3

[0059] This application further proposes that the dynamic control module performs at least one of the following operations: in the molding process, when the temperature sensor deviates from the set value by ±5% for three consecutive sampling cycles, PID closed-loop regulation is activated and the conveyor belt speed is reduced by 10%-15%; when the health index of the elastic material slitting equipment is lower than 0.7, the system automatically switches to the standby tool and generates a maintenance work order; and the nonwoven fabric raw material supply rate is dynamically adjusted according to real-time production fluctuation data to keep the inventory turnover rate in the range of 85%-92%.

[0060] Among them, PID closed-loop control refers to real-time correction of temperature deviation through proportional-integral-derivative algorithms. Specifically, it can be implemented using the PID module built into the industrial controller to quickly eliminate the impact of temperature fluctuations on sealing quality.

[0061] The health index is a score of equipment operating status calculated from sensor data. It can be implemented using a weighted scoring model to quantitatively assess the degree of equipment performance degradation.

[0062] Inventory turnover rate is the ratio of raw material usage to total inventory per unit of time. It can be achieved through a material consumption rate and replenishment cycle matching model, and is used to maintain production continuity and reduce warehousing costs.

[0063] Specifically, in the sealing process, continuous temperature monitoring data triggers the PID controller to output a compensation signal, while the transmission mechanism executes a deceleration command to form a dual regulation mechanism to avoid insufficient sealing strength due to temperature overshoot.

[0064] When the health of the slitting equipment declines, the control system automatically switches to the backup blade and generates a maintenance task to prevent blade failure from causing a decrease in material cutting accuracy. By collecting production data in real time, the raw material supply system dynamically matches the consumption rate to ensure that the production rhythm and material supply remain synchronized, preventing raw material accumulation or shortages.

[0065] Compared to existing technologies, current production systems typically employ single-parameter threshold alarms, failing to achieve multi-level collaborative control. This solution establishes a linkage mechanism between temperature regulation, equipment switching, and raw material supply, simultaneously executing compensatory operations upon detecting abnormal operating conditions. Compared to traditional single-point control methods, it offers faster response speeds and more comprehensive parameter coverage.

[0066] Through the above technical solutions, this application effectively solves the problem of product quality fluctuations under abnormal equipment operating conditions. Closed-loop control maintains the stability of key process parameters, reducing product defects caused by equipment performance degradation. The automatic switching mechanism reduces the probability of unplanned downtime, and the dynamic raw material matching strategy avoids the risk of production interruption, forming a comprehensive quality control system covering equipment maintenance and material management.

[0067] Example 4

[0068] This application further proposes a quality correlation database containing a correlation model between equipment vibration amplitude and the fracture strength of underwear seams, a quantitative relationship table between temperature and humidity parameters of the sterilization process and microbial residue, and a regression analysis function for the wear degree of slitting tools on the material loss rate.

[0069] Among them, the correlation model between equipment vibration amplitude and the breaking strength of underwear seams refers to the mathematical relationship model between equipment vibration parameters and product seam strength established through statistical analysis methods. Specifically, it can be implemented using multiple linear regression. This model is used to guide the adjustment of equipment vibration control parameters.

[0070] The quantitative relationship table between temperature and humidity parameters in the sterilization process and microbial residue refers to a mapping table established based on experimental data between temperature and humidity combinations and microbial detection results. Specifically, data samples can be generated using orthogonal experimental design. This table provides a standardized basis for setting sterilization process parameters.

[0071] The regression analysis function of slitting tool wear on material loss rate refers to the fitting function between tool wear monitoring data and raw material loss data. Specifically, it can be implemented using a multinomial regression algorithm. This function is used to predict the tool replacement cycle.

[0072] Specifically, the correlation model between equipment vibration amplitude and joint fracture strength establishes a negative correlation between vibration amplitude and joint strength by collecting vibration sensor data in real time and combining it with destructive tensile test results. When the vibration amplitude exceeds a threshold, equipment vibration reduction measures are automatically triggered. The quantitative relationship table between sterilization process temperature and humidity parameters and microbial residue is based on microbial culture experiment results under different temperature and humidity combinations, forming a visual control standard for sterilization effect. When abnormal microbial residue is detected, the temperature and humidity control deviation of the sterilization equipment can be traced back. The regression analysis function of slitting tool wear on material loss rate establishes a quadratic function relationship by periodically measuring the wear of the tool edge and combining it with raw material scrap weighing data. When the function's predicted value exceeds the upper limit of material loss, a tool replacement instruction is generated.

[0073] Compared to existing technologies, traditional quality management systems only record equipment operating parameters and quality inspection results, without establishing mathematical models between these parameters. This results in defect tracing relying on manual experience analysis. This solution constructs quantitative models across three dimensions: equipment vibration-joint strength, temperature and humidity-microbial residue, and tool wear-material loss. This enables automatic mapping between equipment status parameters and quality indicators, reducing defect root cause location time by approximately 60%.

[0074] Through the above technical solution, this application solves the technical problem of unclear correlation between equipment status and product quality. It can quickly determine the risk of joint strength defects based on equipment vibration data, match microbial control standards in real time with temperature and humidity parameters, and accurately predict raw material loss trends based on tool wear, thereby realizing automated traceability and preventive control of quality problems.

[0075] Example 5

[0076] After data acquisition, the data acquisition module performs status analysis on the production equipment and uses production output as a status evaluation parameter. If the status evaluation parameter is within a set threshold range, the production equipment is set to normal operation, and the IoT module continues production according to the current production line operation settings. Conversely, if the status evaluation parameter is outside the set threshold range, the production equipment is set to abnormal operation, the IoT module adjusts the current production line operation settings, and marks the current output and production rate as abnormal information. After abnormal information labeling, the production line capacity is monitored, and the range of capacity decrease during production line adjustment and increase phases is collected. Capacity is based on the current... The ratio of the production cycle speed to the set workload speed is used as an evaluation parameter. If the production line capacity decreases by less than the set threshold, the production line capacity is considered qualified. Conversely, if the production line capacity decreases by more than the set threshold, the production line capacity is considered unqualified. The IoT module analyzes the distribution of downtime of production line equipment. If the distribution of downtime is irregular, there is a fluctuation in the equipment operation cycle. The IoT module resets the equipment operation cycle. If the distribution of downtime is regular, it is inferred that abnormal information affects the production line operation. That is, after the IoT module completes the production line adjustment, it predicts abnormal information in advance and makes advance adjustments to the production line after the prediction.

[0077] When in use, the data acquisition module of this invention can acquire output, abnormal information, efficiency, downtime, temperature, pressure, conveying speed and visual data in real time.

[0078] The status analysis module uses machine learning to analyze equipment status and calculate health; the dynamic control module adjusts operating parameters based on health; and the quality association database stores the mapping relationship between equipment status and quality indicators, triggering quality traceability.

[0079] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A disposable underwear manufacturing management system based on production equipment status analysis, characterized in that, Including the management center, which connects to: The data acquisition module acquires real-time data on output, anomalies, efficiency, downtime, temperature, conveyor speed, and visual data. The status analysis module uses machine learning to analyze the device status and calculate its health. The dynamic control module adjusts operating parameters based on the health status. A quality-related database stores the mapping relationship between device status and quality indicators, triggering quality traceability.

2. The disposable underwear manufacturing management system based on production equipment status analysis according to claim 1, characterized in that, The data acquisition module is a multi-source sensor network deployed on the production line, which collects data through distributed sensors.

3. The disposable underwear manufacturing management system based on production equipment status analysis according to claim 1, characterized in that, The operating parameters of the production line equipment are transmitted to the edge computing nodes in real time through a distributed sensor network; temperature sensors monitor the temperature distribution on the surface of the hot press plate, and image acquisition devices capture the flatness characteristics of the material conveying; after normalization, the collected data are input into a convolutional neural network to extract the feature vector of the equipment operating status.

4. The disposable underwear manufacturing management system based on production equipment status analysis according to claim 3, characterized in that, The status analysis module comprises a combined architecture of edge computing units, cloud analysis units, and anomaly detection algorithms. The edge computing unit refers to the data processing unit deployed at the network edge, which is physically close to the production equipment. The cloud analysis unit refers to the time-series data analysis module deployed on a remote server. The anomaly detection algorithm is a composite algorithm that integrates unsupervised learning and dynamic data analysis.

5. A disposable underwear manufacturing management system based on production equipment status analysis according to claim 4, characterized in that, The edge computing unit first performs noise reduction on the temperature and vibration signals, forming lightweight feature vectors that are then uploaded to the cloud. After receiving the feature vectors, the cloud analysis unit analyzes the changing trends of device parameters using a pre-trained LSTM network and calculates the probability distribution of the remaining service life. Simultaneously, the anomaly detection algorithm performs spectral slicing on the periodic vibration signals, uses a sliding window to divide the working cycle, and constructs an isolated tree model within each window to identify spectral distortion features. The collaborative work of these three components enables a multi-dimensional assessment of the device's status.

6. A disposable underwear manufacturing management system based on production equipment status analysis according to claim 5, characterized in that, The operation process of the dynamic control module is as follows: In the sealing process, continuous temperature monitoring data triggers the PID controller to output a compensation signal, while the transmission mechanism executes a speed reduction command to form a dual regulation mechanism to avoid insufficient sealing strength due to temperature overshoot; by collecting production data in real time, the raw material supply system dynamically matches the consumption rate to ensure that the production rhythm and material supply are synchronized, preventing raw material accumulation or shortage.

7. A disposable underwear manufacturing management system based on production equipment status analysis according to claim 6, characterized in that, After data acquisition, the data acquisition module performs status analysis on the production equipment and uses production output as a status evaluation parameter. If the status evaluation parameter is within a set threshold range, the production equipment is set to normal operation, and the IoT module continues production according to the current production line settings. Conversely, if the status evaluation parameter is outside the set threshold range, the production equipment is set to abnormal operation, the IoT module adjusts the current production line settings, and marks the current output and production rate as abnormal information. After abnormal information labeling, the production line capacity is monitored, and the range of capacity decrease during production line adjustment and increase phases is collected. Capacity is based on the current output... The ratio of the production rate of the production cycle to the production rate of the set workload is used as an evaluation parameter. If the range of the production line capacity decrease does not exceed the set range threshold, it is inferred that the production line capacity is qualified; otherwise, if the range of the production line capacity decrease exceeds the set range threshold, it is inferred that the production line capacity is unqualified. The IoT module analyzes the distribution of downtime of production line equipment. If the distribution of downtime is irregular, there is a fluctuation in the equipment operation cycle. The IoT module resets the equipment operation cycle of the production equipment. If the distribution of downtime is regular, it is inferred that abnormal information of the production line affects the operation of the production line. That is, after the IoT module completes the production line adjustment, it predicts abnormal information in advance and makes advance production line adjustments after the prediction.

Images