A method and system for monitoring the operating state of a laser perforator for tipping paper production

Abstract

The present application relates to the technical field of electronic data processing, in particular to a kind of laser puncher operating state monitoring method and system for tipping paper production, comprising: obtaining temperature data sequence, humidity data sequence, current data sequence and resistance data sequence of laser puncher target time;Corresponding temperature data sequence at target time respectively with the deviation degree of current data sequence, humidity data sequence, the difference degree of corresponding temperature data sequence at target time respectively with current data sequence, humidity data sequence;Obtain the influence degree of temperature and humidity on resistance at target time, the deviation degree, difference degree and influence degree are as the input of local outlier factor algorithm, output abnormal score at target time, when abnormal score is greater than or equal to set threshold, determine that laser puncher operating state exists anomaly.The present application solves the problem that the accuracy of abnormal discrimination is not high.

Description

Technical Field

[0001] This invention relates to the field of intelligent early warning technology. More specifically, this invention relates to a method and system for monitoring the operating status of a laser perforation machine used in the production of tipping paper. Background Technology

[0002] In the production of tipping paper, the laser perforating machine is a core processing piece. Its main function is to create uniform, regular, and controllable micro-holes on the paper surface, thereby ensuring that the tipping paper has good air permeability, stable combustion performance, and consistent appearance quality. Compared with traditional mechanical perforation methods, laser perforation not only has the advantages of fast processing speed, high hole diameter consistency, and good positioning accuracy, but also, because it is a non-contact processing method, it can effectively avoid mechanical stress and secondary damage to the paper, significantly improving the overall quality of the finished product and production efficiency. Furthermore, laser perforation technology is more advantageous in terms of process flexibility and controllability. The hole size, density, and distribution can all be flexibly controlled by adjusting process parameters to meet the production needs of different types of tipping paper. Therefore, the laser perforating machine has become an indispensable piece of equipment in the tipping paper manufacturing process, and the stability of its operation directly affects the continuity of the production process and the consistency of product quality.

[0003] During the operation of a laser drilling machine, changes in internal parameters such as temperature, humidity, current, and resistance often serve as precursory signals for malfunctions. Especially under abnormal conditions such as insulation material deterioration, poor contact, or partial discharge, related physical quantities exhibit complex nonlinear changes and coupling relationships. Accurately extracting these changing characteristics and combining them with multi-dimensional data for anomaly detection and early warning is a core challenge currently facing the field of intelligent monitoring. Traditional single-parameter threshold alarm methods, unable to reflect the complex correlations between multiple variables, are prone to missed or false alarms, failing to meet the needs of modern intelligent power equipment. The local outlier factor algorithm, as a density-based unsupervised anomaly detection method, is widely used in industrial equipment fault detection due to its ability to effectively capture anomalies in local neighborhoods.

[0004] However, traditional local outlier factor algorithms still have certain shortcomings in practical applications. They are highly dependent on the quality and selection of input features and have limited ability to fuse and process multidimensional heterogeneous sensor data. They are unable to fully explore the complex multivariate coupling relationships of devices in the operating environment, which leads to low accuracy in anomaly detection. Summary of the Invention

[0005] To address the issues of insufficient accuracy and stability in anomaly detection mentioned in the background art, the present invention provides solutions in the following aspects.

[0006] In a first aspect, the present invention provides a method for monitoring the operating status of a laser punching machine for tipping paper production, comprising: acquiring temperature data sequences, humidity data sequences, current data sequences, and resistance data sequences of the laser punching machine within a set neighborhood time window centered on a target time; calculating the degree of deviation of the temperature data sequence at the target time from the current data sequence and the humidity data sequence, respectively, and the degree of difference between the temperature data sequence at the target time and the current data sequence and the humidity data sequence, respectively; and acquiring the degree of influence of temperature and humidity on resistance at the target time, wherein the degree of influence shows a decreasing trend with respect to the resistance data sequence. The values ​​are positively correlated with the degree of difference between the temperature data sequence and the humidity data sequence; the degree of deviation, degree of difference and degree of influence are used as inputs to the local outlier factor algorithm, and the outlier score at the target time is output. When the outlier score is greater than or equal to the set threshold, it is determined that there is an abnormality in the operation of the laser drilling machine, and the alarm device is triggered to provide early warning.

[0007] The above technical solution integrates multi-dimensional environmental and electrical parameters such as temperature, current, humidity and resistance to comprehensively construct a collaborative feature system that characterizes the operating status of a laser drilling machine. It effectively depicts potential thermal-electrical-humidity coupling anomalies, which not only significantly improves the accuracy and robustness of anomaly detection, but also has strong adaptability and real-time early warning response capabilities.

[0008] Furthermore, The degree of deviation between the temperature data sequence and the current data sequence at a given time. for: , For The temperature data sequence and the current data sequence within a time window centered on time. distance, It is a Gaussian function. For The time-centered neighborhood time window Temperature values ​​at each sampling point For The time-centered neighborhood time window Current values ​​at each sampling point , respectively with The maximum value of the Gaussian function corresponding to the temperature and current data sequences within a defined neighborhood time window centered on a specific time. For The number of sampling points within a neighborhood time window centered on the time setting. This is the preset first hyperparameter.

[0009] The aforementioned technical solution constructs a deviation index that comprehensively measures the degree of synergistic anomaly between temperature and current. At the time series level, it introduces a dynamic time warping distance to characterize the synchronicity of the two types of data in their temporal trends, enabling the model to identify synergistic changes in trends. At the numerical level, it quantifies the degree to which each data point deviates from its normal distribution using a Gaussian function, allowing the model to perceive the degree of anomaly in the data values. The combination of these two approaches not only enhances the ability to express complex, nonlinear coupling characteristics but also significantly strengthens the ability to identify potential abnormal relationships between partial discharge and temperature rise, ultimately achieving more accurate modeling and discrimination of thermoelectric synergistic anomalies in the operating state of laser drilling machines.

[0010] Furthermore, The degree of difference between the temperature data series and the humidity data series at a given time. for: , , These are the sums of all positive terms in the temperature difference sequence and the humidity difference sequence, respectively. , These are the absolute values ​​of the sum of all negative terms in the temperature difference series and the humidity difference series, respectively. To preset the second hyperparameter, , These are the mean values ​​of all elements in the temperature data series and the humidity data series, respectively. for The Euclidean distance between the temperature data series and the humidity data series at a given time.

[0011] The aforementioned technical solution constructs an index that comprehensively measures the dynamic differences between temperature and humidity by simultaneously considering the cumulative intensity of positive and negative changes in the temperature and humidity difference sequences, their mean levels, and their overall Euclidean distance in the feature space. Separating the calculation of positive and negative terms not only distinguishes between increasing and decreasing trends but also enhances sensitivity to the direction of parameter changes; the introduction of the mean term helps reflect the coupling strength of the overall environmental level; and the Euclidean distance, as a normalization factor, suppresses the interference of drastic fluctuations on the final result. Through the fusion of these multiple factors, it is possible to accurately capture coupling anomalies between environmental variables in terms of numerical amplitude and changing trends, effectively improving the ability to identify potential humidity and heat imbalance problems in the operating environment of laser drilling machines.

[0012] Furthermore, The degree of influence of temperature and humidity on resistance at any given time : , for The resistance data sequence at that time shows a downward trend. value, To find the maximum value function, for The degree of difference between the temperature data series and the humidity data series at a given time. For The time-centered neighborhood time window The degree of difference between the temperature data sequence and the humidity data sequence corresponding to each sampling point. for The resistance value at time t. For The time-centered neighborhood time window The resistance value at each sampling point For The number of sampling points within a neighborhood time window centered on the time.

[0013] The aforementioned technical solution introduces a statistically significant indicator of the decreasing trend in the resistance sequence, combined with the nonlinear mapping relationship between temperature and humidity and resistance changes, to construct a comprehensive indicator that reflects the degree of influence of temperature and humidity changes on resistance. This indicator considers both the intensity of environmental deviation and the relative change in resistance value during calculation, and amplifies the nonlinear response characteristics of resistance decrease caused by temperature increase through an exponential function, effectively enhancing the model's ability to detect potential insulation degradation or conductor aging. Furthermore, the introduction of a maximum value function makes the indicator more robust to local abrupt changes or abnormal fluctuations, thereby improving the sensitivity and accuracy of anomaly detection.

[0014] Furthermore, the temperature, humidity, current, and resistance data are standardized and missing values ​​are filled in.

[0015] The aforementioned technical solution effectively improves data quality and computational stability by standardizing and imputing missing values ​​in multi-source sensor data. Standardization eliminates numerical shifts caused by differences in dimensions between different physical quantities, ensuring comparability of various parameters in subsequent modeling and preventing a single dimension from dominating model judgments due to an excessively large numerical range. Simultaneously, imputation of missing values ​​guarantees the integrity of time-series data, preventing abnormal interruptions or misjudgments caused by data breakpoints during local calculations, distance measurements, or model input.

[0016] Furthermore, the temperature difference sequence and humidity difference sequence are obtained by performing first-order difference on the temperature data sequence and humidity data sequence.

[0017] Furthermore, the aforementioned The value was obtained using the Wilcoxon signed-rank test algorithm.

[0018] Furthermore, the alarm device is an audible and visual alarm.

[0019] Furthermore, the set threshold is 1.5.

[0020] In a second aspect, the present invention provides a laser punching machine operation status monitoring system for tipping paper production, comprising a memory and a processor, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the laser punching machine operation status monitoring method for tipping paper production described above is implemented.

[0021] The beneficial effects of this invention are as follows:

[0022] This invention constructs an intelligent early warning mechanism that integrates multiple parameters, comprehensively considering the collaborative deviation relationship, degree of difference, and intensity of influence among key operating environment data such as temperature, current, humidity, and resistance. This not only improves the automation level of intelligent monitoring of the operating status of laser drilling machines, but also significantly enhances the ability to perceive potential anomalies under complex operating conditions of laser drilling machines, and has important engineering application value for ensuring the safe operation of equipment. Attached Figure Description

[0023] Figure 1 This is a flowchart schematically illustrating a method for monitoring the operating status of a laser punching machine for tipping paper production according to an embodiment of the present invention;

[0024] Figure 2 This is a schematic block diagram illustrating the structural structure of a laser perforation machine operation status monitoring system for tipping paper production according to an embodiment of the present invention. Detailed Implementation

[0025] An embodiment of a method for monitoring the operating status of a laser punching machine used in the production of tipping paper.

[0026] like Figure 1 As shown, a flowchart of a laser punching machine operation status monitoring method for tipping paper production according to an embodiment of the present invention includes the following steps:

[0027] S1: Acquire the temperature data sequence, humidity data sequence, current data sequence, and resistance data sequence of the laser drilling machine within a set neighborhood time window centered on the target time.

[0028] In a preferred embodiment, multiple sensing devices installed inside the laser drilling machine collect key environmental variables and electrical parameters in real time during the machine's operation. Temperature data is acquired in real time using a high-precision temperature sensor installed near a heat source or heat accumulation area to reflect the internal heat distribution of the laser drilling machine. Humidity data is collected by a humidity sensor to reflect the changing trend of moisture content in the operating environment, providing an important reference for judging changes in insulation performance. Current data is collected by a current transformer installed on the main circuit, focusing on current disturbance signals caused by partial discharge, abnormal load, or poor contact, effectively reflecting potential partial discharge, short circuit, or grounding problems in the power distribution system. Resistance data is acquired by a resistance tester, mainly used to reflect the conductivity and changing trend of various contact points and conductor connections within the laser drilling machine, indirectly reflecting potential hazards such as corrosion, aging, or moisture.

[0029] To meet the real-time and high-frequency monitoring requirements of industrial sites, this application sets the sampling interval for the above four types of parameters to 1 second, ensuring that a complete data point for temperature, humidity, current, and resistance can be obtained every second, thereby achieving high temporal resolution perception of the laser drilling machine's operating environment. It is worth noting that this sampling interval is configurable; users can flexibly adjust the sampling frequency according to actual needs such as equipment importance, operational stability, and data processing capabilities, to balance data accuracy and resource consumption.

[0030] In actual data acquisition, factors such as electromagnetic interference, signal blockage, sensor malfunction, and unstable data transmission may cause issues like missing data points, abrupt changes, or abnormal fluctuations in the raw data. To improve the accuracy and robustness of subsequent analysis, this application introduces standardization and missing value imputation in the data processing stage. Specifically, for missing values ​​in the data, this application preferably uses linear interpolation to imput them. This method estimates based on the linear trend between adjacent valid data points, enabling the recovery of missing data points without introducing additional noise, effectively avoiding analytical bias or model misjudgment caused by data breakpoints. Linear interpolation in this application has advantages such as simple implementation, high computational efficiency, and smooth interpolation results, making it suitable for real-time data repair needs under high-frequency acquisition conditions.

[0031] To further improve the comparability between different types of data, this application also performed maximum and minimum normalization on the four types of data obtained after interpolation. Since physical quantities such as temperature, humidity, current, and resistance have different units and numerical ranges, directly participating in deviation analysis or anomaly detection algorithm calculations can easily affect the algorithm's convergence speed and recognition accuracy due to inconsistent dimensions or excessively large differences in absolute values. After normalization, all data are uniformly mapped to the [0,1] interval, which not only improves the balance of the feature space but also avoids a single parameter causing dominant interference to the overall analysis.

[0032] S2: Calculate the degree of deviation between the temperature data sequence and the current data sequence and the humidity data sequence at the target time, respectively, and the degree of difference between the temperature data sequence and the current data sequence and the humidity data sequence at the target time.

[0033] In a preferred embodiment, when the internal insulation of the laser drilling machine deteriorates or there is poor contact, a significant partial discharge phenomenon will occur, accompanied by an abnormal rise in temperature. This electrical-thermal coupling effect has obvious spatiotemporal correlation characteristics, that is, the discharge activity will lead to an increase in the local temperature gradient, and the temperature rise will accelerate the deterioration of the insulation material, forming a positive feedback loop. In order to accurately capture this synergistic anomaly, this application constructs a deviation degree.

[0034] The degree of deviation between the temperature data sequence and the current data sequence at a given time. for: , For The temperature data sequence and the current data sequence within a time window centered on time. distance, It is a Gaussian function. For The time-centered neighborhood time window Temperature values ​​at each sampling point For The time-centered neighborhood time window Current values ​​at each sampling point , respectively with The maximum value of the Gaussian function corresponding to the temperature and current data sequences within a defined neighborhood time window centered on a specific time. For The number of sampling points within a neighborhood time window centered on the time setting. This is the preset first hyperparameter.

[0035] By introducing dynamic time warping distance between time series, the synchronicity of temperature and current changes over time is measured. A Gaussian function is then used to assess the deviation of each data point from its normal distribution, thus constructing a comprehensive index reflecting the degree of coordinated anomaly between the two. This index not only captures the similarity of temperature and current trends over time but also sensitively identifies anomalous magnitudes at the numerical level, effectively avoiding the risk of misjudgment based solely on a single feature or simple correlation. In practical applications, this modeling approach, combining time-series trends and statistical deviations, can more accurately reveal potential electrical-thermal coupling anomalies during laser drilling machine operation, improve the ability to identify partial discharge hazards, and achieve more refined and forward-looking intelligent early warning.

[0036] In a preferred embodiment, a high temperature and high humidity environment will significantly accelerate the deterioration process of the internal components of the laser drilling machine. That is, excessive humidity will easily cause surface condensation, resulting in a decrease in resistance, while the increase in temperature will exacerbate the penetration and diffusion of moisture, causing the laser drilling machine to have a compound failure. However, it is difficult to accurately quantify the degree of harm of the temperature and humidity coupling effect on the laser drilling machine using traditional threshold monitoring methods. Therefore, it is necessary to analyze the coupling effect between temperature and humidity to reflect the impact of temperature and humidity on the operating status of the laser drilling machine. Therefore, this application constructs a degree of difference.

[0037] The degree of difference between the temperature data series and the humidity data series at a given time. for: , , These are the sums of all positive terms in the temperature difference sequence and the humidity difference sequence, respectively. , These are the absolute values ​​of the sum of all negative terms in the temperature difference series and the humidity difference series, respectively. To preset the second hyperparameter, , These are the mean values ​​of all elements in the temperature data series and the humidity data series, respectively. for The Euclidean distance between the temperature data sequence and the humidity data sequence at a given time. The temperature difference sequence and humidity difference sequence are obtained by performing first-order differences on the temperature data sequence and the humidity data sequence, respectively.

[0038] By separating positive and negative terms and calculating the proportions of the difference sequences of temperature and humidity data, and combining the mean information and the Euclidean distance between the two, an index that can comprehensively reflect the differences in the changing trends of the two types of environmental variables is constructed. This construction method can not only effectively capture the response differences of temperature and humidity data under small perturbations, but also enhance the ability to identify abrupt or nonlinear changes, and is particularly suitable for reflecting potential risks such as changes in insulation performance caused by moisture or environmental anomalies.

[0039] S3: Obtain the degree of influence of temperature and humidity on resistance at the target time.

[0040] In a preferred embodiment, during the operation of the laser drilling machine, the resistance is affected by temperature and humidity. When the temperature rises, the activity of mobile ions in the resistor increases, leading to a decrease in resistance. When the humidity increases, moisture seeps into the resistor, and due to ionization reactions, hydrogen ions and hydroxide ions are produced, increasing the ion concentration in the resistor and thus reducing resistance. To prevent the laser drilling machine from malfunctioning and causing the power system to malfunction due to the resistance value dropping to a safe threshold, it is necessary to analyze the dynamic change characteristics of the resistance. Therefore, this application constructs an impact assessment method.

[0041] The degree of influence of temperature and humidity on resistance at any given time : , for The resistance data sequence at that time shows a downward trend. value, To find the maximum value function, for The degree of difference between the temperature data series and the humidity data series at a given time. For The time-centered neighborhood time window The degree of difference between the temperature data sequence and the humidity data sequence corresponding to each sampling point. for The resistance value at time t. For The time-centered neighborhood time window The resistance value at each sampling point For The number of sampling points within a designated neighborhood time window centered on a specific time. The value was obtained using the Wilcoxon signed-rank test algorithm.

[0042] By introducing a statistical significance index for resistance change trends, a composite index reflecting the intensity of the influence of temperature and humidity on resistance changes was constructed. This construction logic not only considers the linkage effect between environmental factor changes and electrical characteristics, but also introduces a nonlinear weighting mechanism through a maximum value function and an exponential term. This makes the numerical response of this influencing factor more sensitive and significant when resistance decreases significantly and is accompanied by drastic fluctuations in temperature and humidity. In practical applications, this index can accurately reveal the coupling relationship between potential hazards such as insulation degradation or abnormal conductor contact and environmental changes, thereby improving the laser drilling machine system's ability to perceive complex operating conditions and predict fault evolution trends.

[0043] S4: The deviation degree, difference degree and influence degree are used as inputs to the local outlier factor algorithm, and the abnormal score at the target time is output. When the abnormal score is greater than or equal to the set threshold, it is determined that there is an abnormality in the operation status of the laser drilling machine, and the alarm device is triggered to provide early warning.

[0044] In a preferred embodiment, the operating status of a laser drilling machine is comprehensively characterized from three aspects: trend synchronization, environmental fluctuation, and performance degradation, by constructing three types of feature indicators: deviation degree, difference degree, and impact degree. These indicators are used as input to a local outlier factor algorithm to construct a multi-dimensional feature space. The algorithm compares the local density at the target time with neighboring samples, outputs an anomaly score, and determines whether the operation is abnormal. When the anomaly score exceeds a set threshold, an audible and visual alarm is automatically triggered to provide early warning of anomalies during operation. This not only improves the accuracy of identifying potential faults and the timeliness of early warning but also has strong adaptability and robustness, making it suitable for intelligent monitoring and fault early warning in various operating scenarios.

[0045] In a preferred embodiment, the threshold value is set to 1.5, but it can also be set according to the actual situation.

[0046] This invention integrates multi-dimensional data on temperature, humidity, current, and resistance, combined with time-series dynamic matching and statistical deviation analysis, to construct a multi-level feature index system that comprehensively reflects anomalies in the operating environment of laser drilling machines. Based on the local outlier factor algorithm, it achieves accurate identification and early warning of complex multivariate coupled anomalies. This method effectively captures the coordinated changes among environmental parameters and their impact on resistive performance, improving the sensitivity and accuracy for hidden faults and potential risks. Simultaneously, data preprocessing ensures the integrity and stability of the model input, and it possesses real-time, robust anomaly detection and alarm capabilities, significantly enhancing the operational safety and maintenance efficiency of laser drilling machines, and providing solid technical support for the intelligent management of the equipment.

[0047] An embodiment of a laser perforation machine operation status monitoring system for tipping paper production:

[0048] like Figure 2 As shown in the figure, a structural block diagram of a laser punching machine operation status monitoring system for tipping paper production according to an embodiment of the present invention includes a processor and a memory.

[0049] This invention also provides a system for monitoring the operating status of a laser perforation machine used in tipping paper production. For example... Figure 2 As shown, the system includes a processor and a memory. The memory stores computer program instructions, which, when executed by the processor, implement the above-described method for monitoring the operating status of a laser punching machine for producing tipping paper according to the present invention.

[0050] The laser punching machine operation status monitoring system for tipping paper production also includes other components well known to those skilled in the art, such as communication interfaces. Their settings and functions are known in the art and will not be described in detail here.

[0051] In this invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used or combined with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store desired information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device. Any application or module described in this invention can be implemented using computer-readable / executable instructions stored or otherwise maintained by such a computer-readable medium.

[0052] In the description of this specification, "multiple" or "several" means at least two, such as two, three or more, unless otherwise explicitly specified.

[0053] While this specification has shown and described numerous embodiments of the invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will occur to those skilled in the art without departing from the spirit and essence of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in the practice of this invention.

Claims

1. A method for monitoring the operating status of a laser punching machine used in tipping paper production, characterized in that, include: Acquire the temperature, humidity, current, and resistance data sequences within a set neighborhood time window centered on the target time of the laser drilling machine; Calculate the degree of deviation between the temperature data sequence and the current data sequence and the humidity data sequence at the target time, respectively; and calculate the degree of difference between the temperature data sequence and the current data sequence and the humidity data sequence at the target time, respectively. The influence of temperature and humidity on resistance at the target time is obtained, and the degree of influence shows a decreasing trend with the resistance data sequence. The values ​​are positively correlated with the degree of difference between the temperature and humidity data series; The deviation degree, difference degree, and influence degree are used as inputs to the local outlier factor algorithm, and the outlier score at the target time is output. When the outlier score is greater than or equal to a set threshold, it is determined that there is an abnormality in the operation of the laser drilling machine, and an alarm device is triggered to provide early warning.

2. The method for monitoring the operating status of a laser punching machine for tipping paper production according to claim 1, characterized in that, The degree of deviation between the temperature data sequence and the current data sequence at a given time. for: , For The temperature data sequence and the current data sequence within a time window centered on time. distance, It is a Gaussian function. For The time-centered neighborhood time window Temperature values ​​at each sampling point For The time-centered neighborhood time window Current values ​​at each sampling point , respectively with The maximum value of the Gaussian function corresponding to the temperature and current data sequences within a defined neighborhood time window centered on a specific time. For The number of sampling points within a neighborhood time window centered on the time setting. This is the preset first hyperparameter.

3. The method for monitoring the operating status of a laser punching machine for tipping paper production according to claim 1, characterized in that, The degree of difference between the temperature data series and the humidity data series at a given time. for: , , These are the sums of all positive terms in the temperature difference sequence and the humidity difference sequence, respectively. , These are the absolute values ​​of the sum of all negative terms in the temperature difference series and the humidity difference series, respectively. To preset the second hyperparameter, , These are the mean values ​​of all elements in the temperature data series and the humidity data series, respectively. for The Euclidean distance between the temperature data series and the humidity data series at a given time.

4. The method for monitoring the operating status of a laser punching machine for tipping paper production according to claim 1, characterized in that, The degree of influence of temperature and humidity on resistance at any given time : , for The resistance data sequence at that time shows a downward trend. value, To find the maximum value function, for The degree of difference between the temperature data series and the humidity data series at a given time. For The time-centered neighborhood time window The degree of difference between the temperature data sequence and the humidity data sequence corresponding to each sampling point. for The resistance value at time t. For The time-centered neighborhood time window The resistance value at each sampling point For The number of sampling points within a neighborhood time window centered on the time.

5. The method for monitoring the operating status of a laser punching machine for tipping paper production according to claim 1, characterized in that, The temperature, humidity, current, and resistance data were standardized and missing values ​​were filled.

6. The method for monitoring the operating status of a laser punching machine for tipping paper production according to claim 3, characterized in that, The temperature difference sequence and humidity difference sequence are obtained by performing first-order differences on the temperature data sequence and humidity data sequence, respectively.

7. A method for monitoring the operating status of a laser punching machine for tipping paper production according to claim 4, characterized in that, The The value was obtained using the Wilcoxon signed-rank test algorithm.

8. The method for monitoring the operating status of a laser punching machine for tipping paper production according to claim 1, characterized in that, The alarm device is an audible and visual alarm.

9. A method for monitoring the operating status of a laser punching machine for tipping paper production according to claim 1, characterized in that, The set threshold is 1.

5.

10. A laser punching machine operation status monitoring system for tipping paper production, characterized in that, The device includes a memory and a processor. The memory stores computer program instructions, which, when executed by the processor, implement the method for monitoring the operating status of a laser punching machine for producing tipping paper as described in any one of claims 1 to 9.

Images