Packaging equipment inspection method and system

Abstract

The invention relates to the technical field of data processing, and discloses a packaging equipment inspection method and system. The method comprises the steps that packaging process parameters are collected through multiple sensors, and a working condition data set is formed; extracting abnormal features by using spectral analysis, and generating an operation deviation index; quality and state data are compared to establish an association rule, and a fault precursor feature library is obtained; the station coordination is analyzed through time sequence comparison, and a component state evaluation table is formed; calculating the fault probability of the key component, and generating an inspection point sequence; and making an inspection scheme including parameters, standards and periods, and forming a preventive maintenance plan. According to the method, key parameters such as tension, temperature and speed in the packaging process are analyzed, the early characteristics of the abnormal operation state of the equipment are recognized, the routing inspection priority and the maintenance period are determined in combination with historical fault data and component state evaluation, and conversion from passive maintenance to active prevention is achieved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a packaging equipment inspection method and system. Background Art

[0002] In traditional packaging equipment maintenance and management, equipment inspections are usually carried out in a combination of regular maintenance and post-fault repair. Regular maintenance is the inspection and maintenance of equipment at fixed time intervals, and the maintenance cycle is usually set based on the maintenance manual and experience values ​​provided by the equipment manufacturer; post-fault repair is an emergency repair measure after the equipment has failed or has significantly degraded. This traditional inspection method can guarantee the basic operation of the equipment to a certain extent, but it lacks pertinence and foresight. With the development of automation technology, some packaging equipment has begun to adopt digital monitoring systems, which collect equipment operation data by installing various sensors and use simple threshold judgment methods for abnormal monitoring. This method has improved to a certain extent compared to pure manual inspections and can detect equipment abnormalities more promptly.

[0003] However, the existing inspection methods for packaging equipment have many shortcomings: first, traditional regular maintenance is often carried out according to a fixed cycle, without considering the actual usage status and environmental factors of the equipment, resulting in too frequent maintenance and waste of resources in some cases, and untimely maintenance and missing the best time for fault prevention in other cases; second, although the existing digital monitoring system can collect data, the analysis method is relatively simple, mainly relying on simple threshold judgment, and unable to identify complex failure modes and early signs; third, the various components of the equipment are often treated in isolation during the inspection process, lacking systematic analysis, and ignoring the mutual influence and fault propagation relationship between components; finally, the allocation of inspection resources is not reasonable, and there is no priority sorting according to the importance of components and the risk of failure, resulting in key components not receiving enough attention, while non-critical components consume too many inspection resources. Summary of the invention

[0004] The present application provides a packaging equipment inspection method and system for realizing early prediction and accurate positioning of equipment failures, thereby improving equipment reliability and maintenance efficiency and reducing losses due to unexpected downtime.

[0005] In a first aspect, the present application provides a packaging equipment inspection method, which includes: collecting packaging process parameters through tension sensors, sealing temperature probes, and conveyor belt pulse encoders on the packaging equipment to form a comprehensive data set of packaging equipment working conditions; based on the comprehensive data set of working conditions, using spectrum analysis to extract abnormal packaging material consumption, fluctuations in sealing defective rate, and uneven speed characteristics, and generating a packaging equipment operation deviation index; based on the operation deviation index, establishing association rules by comparing historical data of product quality and equipment status parameters, and obtaining a packaging equipment fault precursor feature library; based on the fault precursor feature library, using a timing comparison method to analyze the coordination of actions between various workstations of the packaging line, and forming a key component status evaluation table for the packaging equipment; based on the key component status evaluation table, combined with historical maintenance records, calculating the failure probability of the cutter, heat seal strip, transmission gear, and motor bearing, and generating a packaging equipment inspection point priority sequence; based on the inspection point priority sequence, formulating an inspection operation guidance plan including detection parameters, judgment criteria, and inspection cycles to form a packaging equipment preventive maintenance plan.

[0006] In a second aspect, the present application provides a packaging equipment inspection system, the packaging equipment inspection system comprising: The acquisition module is used to collect packaging process parameters through the tension sensor, sealing temperature probe, and conveyor belt pulse encoder on the packaging equipment to form a comprehensive data set of packaging equipment working conditions; A generation module is used to extract the abnormal consumption of packaging materials, the fluctuation of sealing defect rate, and the uneven speed by spectrum analysis according to the comprehensive data set of working conditions, and generate the operation deviation index of the packaging equipment; Establishing a module for establishing association rules based on the operation deviation index by comparing the historical data of product quality and equipment status parameters to obtain a feature library of precursors of packaging equipment failures; An analysis module, used to analyze the coordination of actions between various workstations of the packaging line according to the fault precursor feature library by using a time sequence comparison method, and form a status evaluation table of key components of the packaging equipment; A calculation module is used to calculate the failure probability of the cutter, heat seal strip, transmission gear, and motor bearing according to the key component status evaluation table and in combination with historical maintenance records, and generate a priority sequence of inspection points for packaging equipment; The maintenance module is used to formulate an inspection operation guidance plan including detection parameters, judgment criteria, and inspection cycles according to the inspection point priority sequence, so as to form a preventive maintenance plan for packaging equipment.

[0007] The third aspect of the present invention provides a computer device, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the computer device executes the above-mentioned packaging device inspection method.

[0008] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned packaging equipment inspection method.

[0009] In the technical solution provided by the present application, packaging process parameters are collected through tension sensors, sealing temperature probes, and conveyor belt pulse encoders to form a comprehensive working condition data set, and spectrum analysis is used to extract abnormal packaging material consumption, fluctuations in sealing defective rate, and uneven speed characteristics, so as to accurately identify equipment operation deviations at an early stage, and improve the timeliness and accuracy of abnormality detection compared with traditional regular inspection methods; at the same time, by comparing the historical data of product quality and equipment status parameters to establish association rules, a feature library of precursors to packaging equipment failures is obtained, and the association analysis of equipment status and product quality is realized, providing a reliable basis for abnormal status judgment; in addition, the timing comparison method is used to analyze the various processes of the packaging line The coordination of actions between workstations forms a status assessment table for key components of packaging equipment, which overcomes the defect of traditional methods that only focus on single components and ignore the coordination of the system, and can discover potential problems caused by improper coordination between workstations; secondly, the failure probability of cutters, heat seals, transmission gears, and motor bearings is calculated in combination with historical maintenance records, and a priority sequence of inspection points is generated, which realizes the rational allocation of inspection resources and avoids the waste of inspection resources and insufficient maintenance of key components in traditional methods; finally, by formulating an inspection operation guidance plan that includes detection parameters, judgment criteria, and inspection cycles, a preventive maintenance plan is formed, which makes the inspection work standardized and improved the maintenance efficiency and equipment reliability. The present invention applies artificial intelligence algorithms to the field of packaging equipment maintenance, processes multi-source sensor data through advanced algorithms such as multi-scale wavelet decomposition, phase space reconstruction, Lyapunov exponent, nonlinear detrending analysis, etc., and deeply mines complex data with unclear correlation, so that the system can extract valuable fault features from noisy background signals, and establish a fault prediction model through a machine learning algorithm, realizing the transformation from traditional empirical judgment to data-driven decision-making; especially when processing the correlation analysis between equipment status and product quality, the application of hysteresis analysis and time series comparison technology solves the technical problem that traditional methods are difficult to accurately capture the impact of equipment status on product quality, and provides a mathematical basis for accurately predicting the time of fault occurrence; at the same time, in the inspection priority determination link, a decision-making model is established by comprehensively considering multi-dimensional factors such as the remaining life of components, failure risk, and replacement cost, breaking the limitations of traditional fixed-period inspections, realizing a risk-based differentiated inspection strategy, significantly improving the utilization efficiency of maintenance resources and the reliability of equipment operation, and achieving the purpose of reducing equipment failure rate, improving packaging quality, and optimizing maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0011] Figure 1 A schematic diagram of an embodiment of a packaging equipment inspection method in an embodiment of the present application; Figure 2 This is a schematic diagram of an embodiment of a packaging equipment inspection system in an embodiment of the present application; Figure 3 It is a schematic block diagram of the structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0012] The embodiments of the present application provide a packaging equipment inspection method and system. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0013] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 , an embodiment of the packaging equipment inspection method in the embodiment of the present application includes: Step S101, collecting packaging process parameters through the tension sensor, sealing temperature probe, and conveyor belt pulse encoder on the packaging equipment to form a comprehensive data set of packaging equipment working conditions; Step S102: Based on the comprehensive data set of working conditions, the abnormal consumption of packaging materials, the fluctuation of sealing defect rate, and the uneven speed are extracted by spectrum analysis to generate the operating deviation index of the packaging equipment; Step S103: Based on the operation deviation index, association rules are established by comparing the historical data of product quality and equipment status parameters to obtain a feature library of precursors of packaging equipment failures; Step S104: Based on the fault precursor feature library, a time sequence comparison method is used to analyze the coordination of actions between various workstations of the packaging line, and a state evaluation table of key components of the packaging equipment is formed; Step S105: Calculate the failure probability of the cutter, heat seal strip, transmission gear, and motor bearing according to the key component status evaluation table and historical maintenance records, and generate a priority sequence of inspection points for the packaging equipment; Step S106: According to the inspection point priority sequence, formulate an inspection operation guidance plan including detection parameters, judgment criteria, and inspection cycle to form a preventive maintenance plan for packaging equipment.

[0014] It is understandable that the execution subject of the present application may be a packaging equipment inspection system, or a terminal or a server, which is not specifically limited here. The present application embodiment is described by taking a server as the execution subject as an example.

[0015] Specifically, the tension sensor, sealing temperature probe, and conveyor belt pulse encoder on the packaging equipment are used to collect packaging process parameters to form a comprehensive working condition data set. Among them, the tension sensor continuously monitors the tension changes of the packaging material during the transportation process, such as the change in the tensile force of the packaging film between the winding wheel and the feeding wheel; the sealing temperature probe records the temperature fluctuation of the heat seal strip during the sealing process in real time; and the conveyor belt pulse encoder records the packaging line speed change signal. During the collection process, these signals are sampled at multiple points, such as collecting tension data at a frequency of 200 Hz per second, collecting temperature data at a frequency of 50 Hz per second, and collecting speed data at a frequency of 100 Hz per second. Then, the working units are divided according to the operating cycle of the packaging equipment. For example, if each packaging cycle is 2 seconds, each working unit contains 400 tension data points, 100 temperature data points, and 200 speed data points. Then, the key time nodes in the complete packaging cycle are identified, such as the starting time point of material feeding, the starting time point of heat sealing, the time point of the cutter action, etc., and the multi-sensor data are phase-aligned according to these time nodes to eliminate the difference in signal transmission delay and ensure that the data of different sensors can accurately correspond in time. After that, the background interference of the phase-aligned signal is eliminated by the wavelet denoising method to extract the effective working condition signal. Wavelet denoising is to decompose the signal into different frequency components by wavelet transform, then perform threshold processing on the noise component, and reconstruct the denoised signal. A three-dimensional working condition feature space is constructed, and the equipment operation status is mapped with tension-temperature-speed as the coordinate axis. The data point density analysis is performed in this space to form a comprehensive data set of packaging equipment working conditions. According to the comprehensive working condition data set, the abnormal consumption of packaging materials, the fluctuation of sealing defective rate, and the uneven speed are extracted by spectrum analysis to generate the operation deviation index. The tension signal in the comprehensive working condition data set is decomposed by multi-scale wavelet to construct the tension fluctuation feature tree spectrum. Multi-scale wavelet decomposition is to decompose the signal at different scales to obtain the signal features in different frequency ranges. The energy distribution abnormal area is extracted from the tension fluctuation feature tree spectrum, and the material tension peak deviation ratio is calculated to form the abnormal packaging material consumption identification fingerprint. The tension peak deviation ratio refers to the difference ratio between the actual tension peak and the standard tension peak, which reflects whether the packaging material consumption is abnormal. Then the sealing temperature data sequence is reconstructed in phase space and the temperature trajectory attractor diagram is drawn. Phase space reconstruction is to convert a one-dimensional time series into a trajectory in a multidimensional phase space, which is used to analyze the characteristics of nonlinear dynamic systems. By calculating the Lyapunov index of the temperature trajectory attractor graph, the stability of the sealing system is quantified, and a warning index for the fluctuation of the sealing defect rate is established. The Lyapunov index is an indicator of the sensitivity of the system to the initial conditions. The larger the value, the more unstable the system. Then, nonlinear detrending analysis is used on the conveyor belt pulse sequence to extract the hidden mode of small speed fluctuations. Nonlinear detrending analysis is a method to remove the influence of long-term trends in the signal and highlight the characteristics of short-term fluctuations.The hidden mode of tiny speed fluctuations and the characteristic mode during standard operation are cross-correlated to form a speed unevenness characteristic spectrum. Through the multi-dimensional feature space mapping algorithm, the abnormal identification fingerprint of packaging material consumption, the early warning index of sealing defect rate fluctuation and the speed unevenness characteristic spectrum are integrated into the operation deviation index of packaging equipment. Based on the operation deviation index, the association rules are established by comparing the historical data of product quality and equipment status parameters to obtain the characteristic library of packaging equipment failure precursors. The packaging integrity score, sealing strength test value and appearance qualified rate data are extracted from the product quality inspection database to construct the product quality history record matrix. The packaging integrity score is a score for the sealing of the package; the sealing strength test value is the sealing strength value obtained by the tensile test; the appearance qualified rate refers to the proportion of products that pass the appearance inspection. The product quality history record matrix is ​​paired with the operation deviation index corresponding to the time to form a quality-equipment status dual-factor data chain, connecting the product quality index and the equipment status index. The quality-equipment status dual-factor data chain is subjected to hysteresis analysis to determine the time window from the occurrence of operation deviation to the decline of product quality, and form a state-quality impact cycle diagram. Hysteresis analysis is to study the time delay relationship between the change of one variable and the change of another variable. Through the state-quality impact cycle diagram, the development characteristics of different fault types are distinguished and the fault evolution trajectory curve is drawn. The key inflection points and threshold features are extracted from the fault evolution trajectory curve to mark the early warning signal points. The key inflection point is the turning point where the change accelerates during the fault development process, and the threshold feature is the critical value that triggers the warning. The early warning signal points are associated with the specific fault types in the historical maintenance records to obtain the packaging equipment fault precursor feature library.

[0016] According to the fault precursor feature library, the timing comparison method is used to analyze the coordination of the actions between the various stations of the packaging line, and a status evaluation table of the key components of the packaging equipment is formed. The action timing signals of the feeding station, folding station, sealing station, cutting station, and output station are collected from the packaging equipment control system to construct the action time series of the packaging station. The feeding station is responsible for feeding the packaging material; the folding station is responsible for folding the packaging material into shape; the sealing station is responsible for heat-sealing the edge of the packaging; the cutting station is responsible for separating individual packages; and the output station is responsible for outputting the finished product. The action time series of the packaging station is synchronized with the standard timing template in the fault precursor feature library to generate a station action deviation map. Phase synchronization is the process of aligning two time series according to key event points. Based on the station action deviation map, the action conversion delay value between adjacent stations is extracted to form the station connection abnormality measurement value. The action conversion delay value refers to the time interval from the end of one station action to the start of the next station action. The station connection abnormality measurement value is decomposed to identify the source of the mechanism causing the delay and mark the key nodes of the drive chain between stations. The motion characteristics of each key component are analyzed through the key nodes of the drive chain between workstations, and the deviation of the component operation status is calculated. The deviation of the component operation status is the difference between the actual operation status and the ideal status. The deviation of the component operation status is compared with the component health threshold to form a key component status evaluation table for packaging equipment.

[0017] According to the key component status assessment table, the failure probability of the cutter, heat seal strip, transmission gear, and motor bearing is calculated in combination with historical maintenance records, and the priority sequence of inspection points for packaging equipment is generated. The historical failure records of the cutter, heat seal strip, transmission gear, and motor bearing are extracted from the equipment management system to construct a component failure time distribution diagram. The cutter is a device responsible for cutting the packaged material; the heat seal strip is a heating element that forms a seal at the edge of the molten packaging material; the transmission gear is a mechanical component that transmits power; and the motor bearing is a component that supports the rotating part of the motor. The component failure time distribution diagram is compared with the current state parameters in the key component status assessment table to calculate the component remaining life prediction value. The component remaining life prediction value is the time that the component can still work normally based on historical data and current status. Based on the component remaining life prediction value and the component state degradation rate, the component failure risk coefficient is formed. The component state degradation rate is the speed at which the component performance decreases. The component failure risk coefficient is weighted, and the weight factors include the component replacement cost, the impact of downtime, and the availability of spare parts to generate a comprehensive impact score of component failure. According to the comprehensive impact score of component failure, the inspection urgency is divided into three levels: daily inspection items, key focus items, and emergency handling items. Components of different inspection levels are arranged in the order of production line layout to generate a priority sequence of inspection points for packaging equipment. According to the inspection point priority sequence, an inspection operation guidance plan including detection parameters, judgment criteria, and inspection cycle is formulated to form a preventive maintenance plan for packaging equipment. For each component in the inspection point priority sequence, a special detection parameter set is extracted from the standard detection specification library, including the cutter sharpness detection value, the heat seal strip temperature uniformity index, the transmission gear meshing clearance range, and the motor bearing vibration spectrum threshold. The cutter sharpness detection value is an indicator to measure the cutting ability of the cutter; the heat seal strip temperature uniformity index is a measure of the consistency of the heat seal strip temperature distribution; the transmission gear meshing clearance range is the interval range between meshing gears; the motor bearing vibration spectrum threshold is the normal limit of the bearing vibration frequency distribution. The detection parameter set is associated with the abnormal threshold in the fault precursor feature library to construct a component status judgment standard table. Differentiated inspection cycles are set based on the component failure risk coefficient to generate a component inspection time interval matrix. Integrate the detection parameter set, judgment standard table and inspection time interval matrix into component inspection work cards. According to the production plan and maintenance resource allocation, schedule the component inspection work cards and generate the inspection execution calendar. Combine the component inspection work cards with the inspection execution calendar to generate the preventive maintenance plan for packaging equipment.

[0018] Taking the candy packaging line of a food production company as an example, the tension sensor installed on the film roll shaft collected the fluctuation of the packaging film tension within the normal range of 1.5N±0.1N, the sealing temperature probe monitored the heat seal temperature within the set value of 185°C±2°C, and the conveyor belt pulse encoder measured the line speed to maintain at 60 products / minute±1 product / minute. After data processing, it was found that the Lyapunov exponent of the heat seal temperature fluctuation increased from the normal value of 0.05 to 0.12, indicating that the system stability decreased. Through the established fault precursor feature library, similar situations are usually matched to indicate poor contact of the heat seal. Further timing comparison analysis shows that the action conversion delay from the sealing station to the cutting station has increased by 15ms, which is beyond the normal range. It is concluded that the working state deviation of the heat seal reaches 68%, exceeding the health threshold of 60%. Combined with historical data, the heat seal failure risk coefficient is calculated to be 0.78, and the comprehensive impact score of the failure is 85 points, which is a key concern. Therefore, the preventive maintenance plan adjusted the heat seal strip inspection cycle from once a week to once a day, and specified that the inspection temperature uniformity should not exceed ±3°C and the contact pressure should be between 0.4MPa and 0.6MPa to ensure the packaging sealing quality.

[0019] In the embodiment of the present application, the packaging process parameters are collected by tension sensors, sealing temperature probes, and conveyor belt pulse encoders to form a comprehensive working condition data set, and spectrum analysis is used to extract abnormal packaging material consumption, fluctuations in sealing defective rates, and uneven speed characteristics, so as to accurately identify equipment operation deviations at an early stage, and improve the timeliness and accuracy of abnormality detection compared to traditional regular inspection methods; at the same time, by comparing the historical data of product quality and equipment status parameters to establish association rules, a feature library of precursors to packaging equipment failures is obtained, and an association analysis of equipment status and product quality is realized, providing a reliable basis for abnormal state judgment; in addition, a time series comparison method is used to analyze each station of the packaging line The coordination of actions between the two parts is used to form a status assessment table for key components of the packaging equipment, which overcomes the defect of the traditional method that only focuses on a single component and ignores the coordination of the system, and can discover potential problems caused by improper coordination between workstations; secondly, the failure probability of the cutter, heat seal strip, transmission gear, and motor bearing is calculated in combination with the historical maintenance records, and a priority sequence of inspection points is generated, which realizes the reasonable allocation of inspection resources and avoids the waste of inspection resources and insufficient maintenance of key components in the traditional method; finally, by formulating an inspection operation guidance plan including detection parameters, judgment criteria, and inspection cycles, a preventive maintenance plan is formed, which makes the inspection work standardized and improved the maintenance efficiency and equipment reliability. The present invention applies artificial intelligence algorithms to the field of packaging equipment maintenance, processes multi-source sensor data through advanced algorithms such as multi-scale wavelet decomposition, phase space reconstruction, Lyapunov exponent, nonlinear detrending analysis, etc., and deeply mines complex data with unclear correlation, so that the system can extract valuable fault features from noisy background signals, and establish a fault prediction model through a machine learning algorithm, realizing the transformation from traditional empirical judgment to data-driven decision-making; especially when processing the correlation analysis between equipment status and product quality, the application of hysteresis analysis and time series comparison technology solves the technical problem that traditional methods are difficult to accurately capture the impact of equipment status on product quality, and provides a mathematical basis for accurately predicting the time of fault occurrence; at the same time, in the inspection priority determination link, a decision-making model is established by comprehensively considering multi-dimensional factors such as the remaining life of components, failure risk, and replacement cost, breaking the limitations of traditional fixed-period inspections, realizing a risk-based differentiated inspection strategy, significantly improving the utilization efficiency of maintenance resources and the reliability of equipment operation, and achieving the purpose of reducing equipment failure rate, improving packaging quality, and optimizing maintenance costs.

[0020] In a specific embodiment, the process of executing step S101 may specifically include the following steps: (1) Multi-point sampling of the instantaneous tension waveform of the tension sensor during the packaging material conveying process, the temperature curve of the sealing temperature probe during the heat sealing process, and the speed change signal of the conveyor belt pulse encoder; (2) Divide the sampled signals into working units according to the operation cycle of the packaging equipment and identify the key time nodes in the complete packaging cycle; (3) Phase alignment of multi-sensor data based on key time nodes to eliminate signal transmission delay differences; (4) The background interference of the phase-aligned signal is eliminated by wavelet denoising method to extract the effective working condition signal; (5) Construct a three-dimensional working condition feature space and map the equipment operating status using tension-temperature-speed as the coordinate axes; (6) Perform data point density analysis in the three-dimensional working condition feature space to form a comprehensive data set of packaging equipment working conditions.

[0021] Specifically, the instantaneous tension waveform of the tension sensor during the packaging material conveying process, the temperature curve of the sealing temperature probe during the heat sealing process, and the speed change signal of the conveyor belt pulse encoder are sampled at multiple points. Multi-point sampling refers to the process of discretely collecting continuous signals at a certain frequency interval on the time axis. Specifically, the acquisition frequency of the tension sensor is set to 500Hz, that is, 500 data points are collected per second, and the slight changes in the tension of the packaging material are recorded in real time; the acquisition frequency of the sealing temperature probe is 100Hz to capture the dynamic changes in the temperature of the heat sealing strip; the conveyor belt pulse encoder collects speed signals at a frequency of 1000Hz to accurately record the fluctuations in the operating speed of the equipment. Through this high-frequency sampling method, it is possible to obtain subtle change characteristics during the operation of the equipment.

[0022] The sampling signal is divided into working units according to the operation cycle of the packaging equipment to identify the key time nodes in the complete packaging cycle. The working unit refers to the time period in which the packaging equipment completes a complete packaging action, usually with the starting point of the product packaging as the boundary. The key time nodes include the start time of material feeding, the start time of heat sealing, the cutting action time, etc. The method of identifying these time nodes is to analyze the mutation points in the signal characteristic curve, such as the sudden rise point of the tension signal indicates the start of feeding, the rapid rise point of the temperature signal indicates the start of heat sealing, and the short stagnation point of the speed signal indicates the cutting action. By setting the threshold detection algorithm, when the signal change rate exceeds the preset threshold, it is determined to be a key time node. For example, when the tension change rate exceeds 0.5N / ms, it is marked as the material feeding point; when the temperature rise rate exceeds 10℃ / s, it is marked as the heat sealing start point. In this way, the continuous signal data is divided into independent working units for subsequent analysis. Then, the multi-sensor data is phase-aligned according to the key time nodes to eliminate the difference in signal transmission delay. Phase alignment is the process of matching data points collected by different sensors at the same logical moment, solving the time delay problem caused by different physical positions of sensors and different signal transmission paths. The specific implementation method is to use a certain key time node as a reference point and perform time shift alignment on the data of other sensors. For example, based on the heat seal start point, the tension signal and speed signal are shifted by Δt1 and Δt2 respectively, so that the three sets of data are aligned on the time axis. Δt1 and Δt2 are fixed delay values ​​measured experimentally, reflecting the physical delay of signal transmission. After phase alignment, the data of the three sensors at the same logical moment can be directly analyzed in correspondence.

[0023] Subsequently, the background interference of the phase-aligned signal is eliminated by the wavelet denoising method to extract the effective working condition signal. Wavelet denoising is a signal processing method based on wavelet transform, which can effectively remove noise while retaining the main features of the signal. The specific steps include: selecting an appropriate wavelet basis function, such as Daubechies wavelet or Symlet wavelet; performing multi-scale wavelet decomposition on the signal to obtain wavelet coefficients of different frequencies; performing threshold processing on the wavelet coefficients, setting the coefficients less than the threshold to zero; performing wavelet reconstruction to obtain the denoised signal. In the signal processing of the packaging equipment, the 3-level Daubechies4 wavelet decomposition is selected, and the wavelet coefficients are processed by the soft threshold method, and the threshold value is 3 times the standard deviation of the wavelet coefficients. This processing method can effectively remove random noise and electromagnetic interference and retain the important features in the signal. Compared with the original signal, the signal-to-noise ratio of the tension signal, temperature signal and speed signal after denoising is improved by about 10dB.

[0024] Construct a three-dimensional working condition feature space, and map the equipment operating status with tension-temperature-speed as the coordinate axes. The three-dimensional working condition feature space is a Euclidean space with three key parameters as the coordinate axes, and each point represents the operating status of the equipment at a specific moment. The specific construction method is: normalize the signal after noise reduction, unify the three different dimension signals into the [0,1] interval; then establish a three-dimensional coordinate system with the normalized tension value as the x-axis, the temperature value as the y-axis, and the speed value as the z-axis; map the data points at the same moment after phase alignment to this coordinate system to form the trajectory of the equipment operating status. Through mapping, the operating status of the equipment is represented as a trajectory in the three-dimensional space, and the trajectory under normal working conditions usually has stable morphological characteristics. Perform data point density analysis in the three-dimensional working condition feature space to form a comprehensive data set of packaged equipment working conditions. Data point density analysis is a method of statistically analyzing the distribution density of data points in different regions in the three-dimensional space, which is used to identify the main distribution areas and abnormal areas of the equipment operating status. Specifically, the three-dimensional space is divided into grid cells of equal size; then the number of data points contained in each grid cell is counted; based on the number of data points, the main distribution area and degree of deviation of the equipment operating status are determined. The size of the grid cell is determined according to the data accuracy requirements, and is usually selected so that the main distribution area under normal operating conditions contains about 10-20 grid cells. By calculating the statistical characteristics of the data points in each grid cell, such as mean, variance, skewness, kurtosis, etc., the stability and abnormality of the equipment operating status are further quantified to form a comprehensive operating condition data set containing multi-dimensional operating characteristics of the equipment.

[0025] Take a food packaging production line as an example. When the packaging equipment is running, the tension sensor records that the packaging film tension fluctuates between 0.8N and 1.2N, with a sampling frequency of 500Hz; the temperature probe monitors that the temperature of the heat seal strip varies between 175℃ and 180℃, with a sampling frequency of 100Hz; the pulse encoder shows that the equipment runs at a speed of 35 to 37 packs / minute, with a sampling frequency of 1000Hz. Through signal analysis, it is found that a packaging cycle is completed every 2.5 seconds, and the sharp rise point of the temperature signal is used as the heat seal start time node. At the same time, the tension signal drops instantaneously and the speed signal stabilizes briefly. Taking the heat seal start point as the reference point, the tension signal is moved forward by 15ms and the speed signal is moved back by 8ms to achieve phase alignment. The aligned signal is decomposed by 3-level Daubechies4 wavelet to reduce noise, filtering out environmental vibration and electrical interference. The tension, temperature, and speed signals after noise reduction are normalized to the interval [0,1], and a three-dimensional feature space is constructed. It is found that the data points in normal operating conditions are mainly concentrated in the central area of ​​the feature space to form a stable ellipsoid distribution. When foreign matter adheres to the heat seal strip, the data points will shift toward the positive direction of the temperature axis to form a local high-density area. This feature is marked as an early indicator of heat seal abnormality, providing an effective judgment basis for equipment inspection.

[0026] In a specific embodiment, the process of executing step S102 may specifically include the following steps: (1) Perform multi-scale wavelet decomposition on the tension signal in the comprehensive working condition data set and construct a tension fluctuation feature tree spectrum; (2) Extract the energy distribution abnormal area from the tension fluctuation feature tree spectrum, calculate the material tension peak deviation ratio, and form the abnormal consumption fingerprint of packaging materials; (3) Reconstruct the sealing temperature data sequence in phase space and draw the temperature trajectory attractor diagram; (4) By calculating the Lyapunov index of the temperature trajectory attractor graph, the stability of the sealing system is quantified and a sealing defect rate fluctuation warning index is established; (5) Use nonlinear detrending analysis on the conveyor belt pulse sequence to extract the hidden patterns of small speed fluctuations; (6) Perform cross-correlation analysis on the hidden mode of tiny speed fluctuations and the characteristic mode during standard operation to form a speed inhomogeneity characteristic spectrum; (7) Through the multi-dimensional feature space mapping algorithm, the abnormal identification fingerprint of packaging material consumption, the sealing defect rate fluctuation warning index and the speed unevenness feature spectrum are integrated into the packaging equipment operation deviation index.

[0027] Specifically, the tension signal in the working condition comprehensive data set is decomposed by multi-scale wavelet to construct the tension fluctuation feature tree spectrum. Multi-scale wavelet decomposition is a time-frequency analysis technology that can decompose the signal at different scales and extract features in different frequency ranges. The specific implementation steps are: select a wavelet basis function suitable for the tension signal characteristics, such as Daubechies wavelet basis or Morlet wavelet basis; pass the tension signal through high-pass and low-pass filters in turn to obtain detail coefficients and approximate coefficients; continue to decompose the approximate coefficients to obtain the detail coefficients and approximate coefficients of the next level; repeat the above steps to the predetermined number of decomposition levels. Usually, a 5-layer decomposition depth is selected to cover the characteristics of each frequency band from high-frequency noise to low-frequency trends. After decomposition, the tension fluctuation feature tree spectrum formed contains detail coefficient matrices of different frequency levels and approximate coefficient matrices of the lowest frequency. These coefficient matrices jointly describe the complete characteristics of the tension signal in the time-frequency domain. Extract the energy distribution abnormal area from the tension fluctuation feature tree spectrum, calculate the material tension peak deviation ratio, and form the abnormal consumption of packaging materials. The energy distribution abnormal area refers to the area where the signal energy obviously deviates from the normal operating state in certain time-frequency intervals of the feature tree spectrum. The extraction method is: calculate the energy distribution of detail coefficients at each level of the feature tree spectrum, that is, the sum of squares of each coefficient; compare it with the pre-established standard energy distribution during normal operation; when the energy deviation of a certain time-frequency interval exceeds the set threshold, it is marked as an abnormal area. The material tension peak deviation ratio is defined as the difference between the ratio of the actual tension peak to the standard tension peak and 1, which reflects the degree of abnormal tension of the packaging material. The abnormal features detected at each level are combined according to the weighted importance to form a fingerprint for identifying abnormal consumption of packaging materials. This fingerprint can accurately reflect different types of material consumption abnormalities, such as excessive stretching, insufficient relaxation, etc.

[0028] The sealing temperature data sequence is reconstructed in phase space, and the temperature trajectory attractor diagram is drawn. Phase space reconstruction is a method to recover the system dynamic characteristics from a one-dimensional time series. The one-dimensional time series is mapped to a high-dimensional phase space based on the embedding theorem. The specific implementation steps are: determine the embedding dimension m and the time delay τ; construct an m-dimensional vector sequence, each vector consists of m points separated by τ in the original time series; draw these vector points in the m-dimensional phase space to form the system state trajectory. The embedding dimension is usually determined by the false nearest neighbor method, and the time delay is determined by the mutual information method or the autocorrelation function. For the sealing temperature data, the typical embedding dimension is 3 or 4, and the time delay is 10-20 sampling points. In the reconstructed phase space, the temperature change trajectory forms a specific geometric shape, called the temperature trajectory attractor diagram, which reflects the intrinsic dynamic characteristics of the sealing temperature system.

[0029] By calculating the Lyapunov index of the temperature trajectory attractor graph, the stability of the sealing system is quantified, and a warning index for the fluctuation of the sealing defect rate is established. The Lyapunov index is a quantitative indicator that describes the separation rate of adjacent trajectories in a dynamic system. A positive value indicates that the system has chaotic characteristics, and a negative value indicates that the system is stable. The calculation formula of the Lyapunov index is as follows:

[0030] in, represents the Lyapunov exponent, is the number of iterations, is the sampling time interval, represents the initial distance between the ith adjacent trajectory point pair in the phase space, Indicates the distance after one iteration. Based on the correlation analysis between the Lyapunov index and the historical sealing defect rate, the sealing defect rate fluctuation warning index (SDWI) is established:

[0031] in, It is the early warning index of sealing defect rate fluctuation. , , , is the fitting coefficient, is the Lyapunov exponent, is the temperature variation coefficient. When the preset threshold is exceeded, a poor sealing warning is triggered. Nonlinear detrending analysis is used on the conveyor belt pulse sequence to extract hidden patterns of small speed fluctuations. Nonlinear detrending analysis is a method to eliminate the long-term trend of the signal and highlight the short-term fluctuation characteristics. The specific implementation steps are: divide the pulse sequence into several non-overlapping segments; fit a multi-order polynomial trend curve to each segment of data; subtract the trend curve from the original data to obtain a detrended fluctuation sequence; perform statistical analysis on the detrended fluctuation sequence to extract fluctuation characteristics. The polynomial order is usually selected as 3-5, which can effectively capture nonlinear trends. After removing the long-term trend, the hidden patterns of small speed fluctuations will become more obvious, and these patterns often contain important information about the operating status of the equipment.

[0032] The hidden mode of small speed fluctuations and the characteristic mode during standard operation are cross-correlated to form a speed unevenness characteristic spectrum. Cross-correlation analysis is a technology for evaluating the similarity of two signals. The correlation between the signals is obtained by calculating the correlation coefficient under different time delays. The specific implementation steps are: calculate the correlation coefficient under different time delays for the extracted hidden mode of small speed fluctuations and the standard mode; draw a curve of the correlation coefficient changing with time delay; analyze the peak position, peak size and curve shape characteristics of the correlation curve. Cross-correlation analysis can effectively detect abnormal modes in equipment speed changes, such as periodic fluctuations, sudden fluctuations, etc. These features constitute the speed unevenness characteristic spectrum, which directly reflects the health status of the equipment transmission system. Through the multi-dimensional feature space mapping algorithm, the abnormal identification fingerprint of packaging material consumption, the early warning index of sealing defective rate fluctuation and the speed unevenness characteristic spectrum are integrated into the packaging equipment operation deviation index. Multi-dimensional feature space mapping is a technology for unified representation and comprehensive evaluation of multiple heterogeneous features. The calculation formula of the packaging equipment operation deviation index (PODI) is as follows:

[0033] in, Deviation indicators for packaging equipment operation, , , is the weight coefficient of each feature, satisfying + + = 1, MPDF is the fingerprint score for abnormal material consumption, SDWI is the early warning index for sealing defect rate fluctuation, and SVSI is the speed unevenness characteristic spectrum index. The weight coefficient is determined through historical data analysis and expert experience, reflecting the degree of influence of each factor on the equipment status. The higher the PODI value, the greater the deviation of equipment operation, which requires more attention.

[0034] Taking a beverage packaging line as an example, when the tension signal is monitored to fluctuate abnormally during the operation of the equipment, the tension fluctuation feature tree spectrum is constructed through 5-layer Daubechies4 wavelet decomposition, and it is found that there is an abnormal increase in energy in the detail coefficients of the 3rd and 4th layers, and the corresponding frequency range is 5-15Hz, which is usually related to the failure of the packaging film tension control system. The material tension peak deviation ratio is calculated to be 0.28, which exceeds the normal range of 0.1, forming an abnormal identification fingerprint for packaging material consumption. At the same time, the sealing temperature data is reconstructed in phase space, the embedding dimension is selected as 3, and the time delay is 15 sampling points. The temperature trajectory attractor diagram is drawn, and it is found that the trajectory changes from the usual compact ring to a loose spiral. The Lyapunov index is calculated to be 0.15, which is significantly higher than the normal value of 0.05. Substituting this value into the warning index formula, the sealing defect rate fluctuation warning index is 0.68, which is close to the warning threshold of 0.7. The nonlinear detrending analysis of the conveyor belt pulse sequence was performed to extract the periodic fluctuation mode, and the cross-correlation analysis with the standard mode was performed. It was found that the peak value of the correlation curve decreased and the position shifted, indicating that the synchronization of the transmission system decreased. Combining these three indicators, the operation deviation index of the packaging equipment was calculated to be 0.58, which exceeded the normal operation threshold of 0.4, indicating that the tension control system and the transmission system need to be inspected and maintained to prevent possible packaging quality problems.

[0035] In a specific embodiment, the process of executing step S103 may specifically include the following steps: (1) Extract packaging integrity scores, seal strength test values, and appearance pass rate data from the product quality inspection database to construct a product quality history record matrix; (2) Pair the product quality history record matrix with the operation deviation index corresponding to the time in time series to form a dual-factor data chain of quality and equipment status; (3) Conduct hysteresis analysis on the dual-factor data chain of quality and equipment status to determine the time window from the occurrence of operating deviation to the decline of product quality, and form a status-quality impact cycle diagram; (4) Grouping through the state-quality impact cycle diagram, distinguishing the development characteristics of different fault types, and drawing the fault evolution trajectory curve; (5) Extract key inflection points and threshold features from the fault evolution trajectory curve and mark early warning signal points; (6) Associate the early warning signal points with the specific fault types in the historical maintenance records to obtain a feature library of precursors to packaging equipment failures.

[0036] Specifically, the packaging integrity score, sealing strength test value, and appearance pass rate data are extracted from the product quality inspection database to construct a product quality history matrix. The packaging integrity score is a quantitative evaluation of the packaging sealing performance through methods such as air tightness test and water immersion test, usually expressed in 0-100 points; the sealing strength test value is the tensile strength of the sealing seam when subjected to tension measured by a tensile tester, in Newton (N); the appearance pass rate data refers to the proportion of the number of qualified products in the product appearance inspection to the total number of inspections. These three indicators together reflect different aspects of product packaging quality. The method of constructing a product quality history matrix is ​​to arrange these three indicators in time series to form an n×4 matrix, where n is the number of historical data points, and the 4 columns are time, packaging integrity score, sealing strength test value, and appearance pass rate. Each row in the matrix represents the product quality status at a time point. This matrix structure facilitates subsequent time series matching with equipment status data. The product quality history matrix is ​​time-series paired with the operation deviation indicator corresponding to the time to form a quality-equipment status dual-factor data chain. The operation deviation index is generated in the previous steps, and includes multi-dimensional information such as abnormal identification fingerprint of packaging material consumption, early warning index of sealing defect rate fluctuation and speed uneven characteristic spectrum. The method of time series pairing is to match product quality data and equipment operation data one by one according to the timestamp. When the collection time of product quality data and equipment operation data is not completely consistent, the nearest time point matching or linear interpolation method is used for pairing. The quality-equipment status two-factor data chain formed after pairing is a comprehensive data structure that includes product quality indicators and equipment operation status indicators. Each data point contains timestamp, quality indicators (packaging integrity score, sealing strength test value, appearance qualification rate) and equipment status indicators (operation deviation indicators). This data chain structure can clearly reflect the correlation between product quality and equipment status.

[0037] Then, the quality-equipment status dual-factor data chain is subjected to hysteresis analysis to determine the time window from the occurrence of operation deviation to the decline of product quality, and to form a state-quality impact cycle diagram. Hysteresis analysis is a method for studying the time delay relationship between the change of one variable in sequence data and the change of another variable. The specific implementation steps are: time-shift the equipment operation deviation index sequence to construct a sequence with different lag times; calculate the correlation coefficient between the operation deviation index and the product quality index under each lag time; draw a curve of the correlation coefficient changing with the lag time, that is, the lag correlation diagram; determine the lag time when the correlation coefficient reaches the maximum value or exceeds the significance threshold. Through this analysis, the time window for the change of equipment status to affect product quality can be determined, that is, the time required from the abnormal equipment status to the decline of product quality. This time window is of great significance for predictive maintenance, which determines the maximum allowable time from the detection of equipment abnormality to the maintenance measures that must be taken. The hysteresis analysis results form a state-quality impact cycle diagram, which intuitively shows the time relationship between different equipment status indicators and different product quality indicators. Grouping is carried out through the state-quality impact cycle diagram to distinguish the development characteristics of different fault types and draw the fault evolution trajectory curve. The grouping method is based on the time relationship characteristics in the state-quality impact cycle diagram, and historical failure cases are clustered according to similarity. Common clustering algorithms include K-means clustering, hierarchical clustering, etc. The characteristics considered during clustering include: the rate of change of equipment status indicators, the decline of product quality indicators, the length of the impact time window, etc. The clustering results represent different fault types or fault development modes. For each type of fault, a typical case is selected, and a curve of the change of equipment status indicators and product quality indicators over time is drawn from the entire process from the abnormal equipment status to the final failure, that is, the fault evolution trajectory curve. The curve reflects the complete development process of different fault types from early signs to final failure.

[0038] Then, the key inflection points and threshold features are extracted from the fault evolution trajectory curve to mark the early warning signal points. The key inflection point refers to the point where the change trend in the fault evolution trajectory curve changes significantly, which usually indicates that the fault development has entered a new stage. Methods for extracting key inflection points include curve slope analysis method, curvature calculation method, etc. Specifically, the trajectory curve is smoothed to remove the impact of short-term fluctuations; then the first-order derivative (slope) and second-order derivative (curvature) of the curve are calculated; and the points where the slope or curvature changes significantly are identified by setting thresholds. The threshold feature refers to the characteristic point when the equipment status indicator or product quality indicator reaches a specific value, indicating that the equipment is in a specific fault development stage. These characteristic points are usually determined based on historical data statistics and expert experience. The key inflection point and threshold features together constitute the early warning signal points, which are the indicators and values ​​that need to be focused on in equipment status monitoring.

[0039] The early warning signal points are associated with the specific fault types in the historical maintenance records to obtain the packaging equipment failure precursor feature library. The historical maintenance records contain information such as the specific fault type, fault location, and maintenance measures when the equipment fails. The method of association annotation is to establish a corresponding relationship between each early warning signal point and the fault type in the historical maintenance record to form an early warning rule that "if the equipment status indicator reaches the first threshold and the product quality indicator is lower than the second threshold, the equipment may be about to have a Class P failure." These rules are statistically verified to ensure the accuracy and timeliness of their warnings. All early warning rules constitute the packaging equipment failure precursor feature library, which is an important knowledge base for equipment status monitoring and preventive maintenance.

[0040] Taking a biscuit packaging line as an example, by analyzing the production data of the past year, product quality data such as packaging integrity score (full score 100 points), sealing strength test value (unit: Newton) and appearance qualification rate (percentage) were extracted from the quality inspection database, and a product quality history record matrix containing 365 days, 3 shifts per day and a total of 1095 rows of data was constructed. At the same time, the equipment operation deviation index data of the same period were collected, and the two sets of data were integrated into a quality-equipment status dual-factor data chain through timestamp matching. After a lag analysis of the data chain, it was found that there was an 8-hour lag relationship between the heat seal strip temperature fluctuation index and the packaging integrity score, that is, after the heat seal strip temperature fluctuated abnormally, the packaging integrity score would not show a significant decrease until about 8 hours later; there was a 4-hour lag relationship between the tension control deviation and the sealing strength test value; there was a 2-hour lag relationship between the uneven speed of the transmission system and the appearance qualification rate. According to these lag time characteristics, historical fault cases are divided into three categories: heat seal system fault category, tension control system fault category and transmission system fault category. For heat seal system failures, trajectory curves of the heat seal strip temperature uniformity index, sealing temperature fluctuation amplitude, and packaging integrity score over time were drawn. Key inflection points were identified from the trajectory curves: when the heat seal strip temperature uniformity index fluctuates from the normal 3°C to above 5°C and lasts for more than 2 hours, it is the first warning point; when the sealing temperature fluctuation amplitude expands from the normal ±2°C to ±4°C and lasts for more than 1 hour, it is the second warning point. These warning points were matched with the 14 historical heat seal strip failure maintenance records, and it was found that the heat seal strip local wear failure occurred an average of 12 hours after the first warning point appeared, and the heat seal strip thermostat failure occurred an average of 6 hours after the second warning point appeared.

[0041] In a specific embodiment, the process of executing step S104 may specifically include the following steps: (1) Collect the action timing signals of the feeding station, folding station, sealing station, cutting station, and output station from the packaging equipment control system to construct the packaging station action time sequence; (2) Synchronize the phase of the packing station action time series with the standard timing template in the fault precursor feature library to generate a station action deviation map; (3) Based on the workstation action deviation map, the action conversion delay values ​​between adjacent workstations are extracted to form a workstation connection abnormality measurement value; (4) Decompose the abnormal measurement values ​​of workstation connection, identify the source of the mechanism causing the delay, and mark the key nodes of the drive chain between workstations; (5) Analyze the changes in the motion characteristics of each key component through the key nodes of the drive chain between workstations and calculate the deviation of the component's operating state; (6) Compare the component operating status deviation with the component health threshold to form a key component status assessment table for packaging equipment.

[0042] Specifically, the action timing signals of the feeding station, folding station, sealing station, cutting station, and output station are collected from the control system of the packaging equipment to construct the action time sequence of the packaging station. The feeding station is responsible for conveying the packaging material into the equipment; the folding station is responsible for folding the packaging material into a preset shape; the sealing station heat-seals or bonds the edge of the package; the cutting station divides the continuous package into independent units; and the output station conveys the completed packaged product out of the equipment. The action timing signal refers to the data record of the start time, duration, and end time of the action performed by each station. The collection method is to install position sensors, photoelectric switches, or encoders on the key driving components of each station to record the precise time point of the action of each station. For example, the feed roller rotation signal of the feeding station, the pressure plate action signal of the folding station, the heat sealing head pressurization signal of the sealing station, the cutter action signal of the cutting station, and the conveyor belt start signal of the output station. These signals are recorded in the form of timestamps and status values ​​(0 or 1) to form the action time sequence of each station. The time series of each workstation are sorted and merged according to time to form a complete packing workstation action time series, which fully records the time sequence relationship of each workstation action during the entire packaging process. The packing workstation action time series is phase-synchronized with the standard time series template in the fault precursor feature library to generate a workstation action deviation spectrum. The standard time series template is a typical workstation action time series under normal operation of the equipment selected from historical data. Phase synchronization refers to the process of aligning two time series according to a specific reference point to eliminate the influence of time offset and facilitate direct comparison of sequence features. The specific implementation steps include: determining the reference synchronization point, usually selecting the starting point of the packaging cycle, such as the feeding start time of the feeding workstation; then aligning the currently collected time series and the standard template at the reference point; calculating the time deviation of each workstation action at the corresponding time point. This deviation calculation adopts a point-to-point comparison method, that is, for each corresponding point in the sequence, the difference between its time value and the time value of the corresponding point in the standard template is calculated. These deviation values ​​are arranged in chronological order and displayed in a graphical manner to form a workstation action deviation spectrum. The graph intuitively shows the timing differences between the current equipment operating status and the standard status. Different deviation patterns often correspond to different types of equipment abnormalities.

[0043] Then, based on the station action deviation map, the action conversion delay values ​​between adjacent stations are extracted to form the station connection abnormality measurement value. The action conversion delay value refers to the time interval between the end of one station action and the start of the next station action. Under normal operating conditions, these delay values ​​should fluctuate within a certain range; when an abnormality occurs in a certain part of the equipment, the delay values ​​between the corresponding stations will change significantly. The extraction method is: identify the start and end time points of each station action from the station action deviation map; then calculate the time interval between adjacent stations, such as the time from the end of the feeding station to the start of the folding station, the time from the end of the folding station to the start of the sealing station, etc.; compare these time intervals with the corresponding intervals in the standard template to calculate the deviation value. The station connection abnormality measurement value is defined as the deviation rate between the actual connection delay and the standard connection delay. This indicator can directly reflect the abnormal degree of coordination between stations. Usually a threshold is set, and when the abnormal measurement value exceeds the threshold, it is judged as a connection abnormality. Decompose the station connection abnormality measurement value, identify the source of the mechanism causing the delay, and mark the key nodes of the drive chain between stations. The decomposition method is based on equipment structure analysis, which decomposes the drive chain between workstations into several key nodes, such as bearings, gears, transmission belts, connecting rods, etc., and then assigns abnormal delay values ​​to these nodes. The specific steps include: establishing a structural model of the equipment drive chain to clarify the power transmission path between each workstation; then locating the abnormal delay through additional sensor information, such as drive motor current, bearing vibration, gear meshing sound and other auxiliary data; combining equipment structure knowledge to determine the most likely mechanism to cause delays. This decomposition analysis can accurately locate the macroscopic workstation connection anomaly to a specific mechanical component, greatly reducing the scope of troubleshooting. The identified key nodes of the drive chain are usually vulnerable or critical mechanism components in the equipment, such as spindle bearings, transmission gears, synchronous pulleys, etc.

[0044] Then, the motion characteristics of each key component are analyzed through the key nodes of the drive chain between workstations, and the component operation state deviation is calculated. The calculation formula of the component operation state deviation (CDSD) is as follows:

[0045] in, is the deviation of component operation status; is the number of key performance parameters; , , is the weight coefficient, satisfying + + = 1; and are the dynamic stiffness parameters under current and standard states respectively; and They are the motion frequency parameters in the current and standard states respectively; and They are the amplitude parameters under the current and standard states, respectively. The dynamic stiffness parameter reflects the characteristics of the component's response to external forces, the motion frequency parameter reflects the periodic characteristics of the component's motion, and the amplitude parameter reflects the amplitude characteristics of the component's motion. These three types of parameters together describe the motion state of the component. This formula weights and synthesizes parameter deviations of different properties to obtain a comprehensive state deviation index. Different weight configurations are used for different types of components. For example, for bearings, the vibration frequency deviation weight is higher; for gears, the dynamic stiffness deviation weight related to meshing clearance is higher.

[0046] The component operation state deviation is compared with the component health threshold to form a key component state evaluation table for packaging equipment. The component health threshold is a critical value of state deviation determined based on historical data and expert experience. Exceeding this value indicates that the component state has entered the abnormal range. The comparison process is: compare the operation state deviation of each key component with the corresponding health threshold, and determine the component health state level based on the relationship between the deviation and the threshold. The health status is usually divided into four levels: normal, slightly abnormal, moderately abnormal, and severely abnormal. The health status evaluation results of all key components are summarized in a table format, including information such as component name, current state deviation, health threshold, health status level, and recommended treatment measures, to form a key component state evaluation table for packaging equipment. The evaluation table is used to display the health status of each key component of the equipment.

[0047] In a specific embodiment, the process of executing step S105 may specifically include the following steps: (1) Extract the historical fault records of cutters, heat seals, transmission gears, and motor bearings from the equipment management system and construct a component failure time distribution map; (2) Compare the component failure time distribution diagram with the current state parameters in the key component state assessment table to calculate the predicted value of the component's remaining life; (3) Based on the predicted value of the remaining service life of the component and the degradation rate of the component state, a component failure risk coefficient is formed; (4) Weighting the component failure risk factor, with weight factors including component replacement cost, downtime impact, and spare parts availability, to generate a comprehensive impact score for component failure; (5) The inspection urgency is divided into three levels: daily inspection items, key focus items, and emergency handling items, according to the comprehensive impact score of component failures; (6) Arrange components of different inspection levels according to the production line layout order to generate a priority sequence of inspection points for packaging equipment.

[0048] Specifically, the historical fault records of cutters, heat seals, transmission gears, and motor bearings are extracted from the equipment management system to construct a component failure time distribution map. The cutter is a sharp component used to cut off the packaging material in the packaging equipment; the heat seal is a heating element that melts and seals the edge of the packaging material by heating; the transmission gear is a toothed mechanical element that transmits power; and the motor bearing is a friction-reducing component that supports the rotating part of the motor. The historical fault records include information such as the installation time of the component, the time of the failure, the type of failure, and the maintenance record. The method for extracting these data is to query the maintenance record database of the equipment management system and filter out all maintenance events related to these four types of key components. The filtered data are classified according to the component type, and the use time of each component from installation to failure is calculated to form a component life data set. Then, the life data of each type of component is statistically analyzed, and the most suitable life distribution model, such as Weibull distribution, lognormal distribution, etc., is determined by using methods such as chi-square fitting. According to the fitted distribution model, a component failure time distribution map is drawn to show the change law of the failure probability of each type of component with the use time. The component failure time distribution map is compared with the current state parameters in the key component state evaluation table to calculate the predicted value of the remaining life of the component. The key component status assessment table is formed in the previous steps and contains information such as the current state deviation of each key component. The method for calculating the remaining life of the component is based on the proportional risk model, taking the current state parameters of the component as covariates and correcting the basic life distribution. The specific steps include: obtaining the basic life distribution parameters of the component from the failure time distribution diagram; then calculating the state adjustment factor according to the state deviation in the status assessment table; correcting the basic life distribution by the state adjustment factor to obtain the remaining life prediction value considering the current state. For example, if the basic average life of a heat seal strip is 2000 hours, the current state deviation is 0.3, and the state adjustment factor obtained by calculation is 0.7, then the remaining life prediction value of the heat seal strip is 2000 hours × 0.7 = 1400 hours. This method combines historical statistical data with the current actual state to improve the accuracy of life prediction. Then, based on the predicted value of the remaining life of the component and the degradation rate of the component state, the component failure risk coefficient is formed. The component state degradation rate refers to the speed at which the component state parameters change over time, which is usually determined by the rate of change of multiple consecutive state monitoring data. The calculation method is to perform linear or nonlinear regression analysis on recent condition monitoring data to obtain the changing trend of the condition parameters over time. The calculation of the component failure risk coefficient comprehensively considers the remaining life prediction value and the state degradation rate. For two components with the same remaining life, the component with a faster state degradation rate has a higher failure risk; similarly, for two components with the same state degradation rate, the component with a shorter remaining life has a higher failure risk. The specific calculation method is to take the inverse of the remaining life prediction value and weighted average it with the state degradation rate to obtain a comprehensive failure risk coefficient.The weight coefficient is determined based on the component type and historical experience. Usually the weight of the state degradation rate is between 0.3 and 0.5.

[0049] The component failure risk coefficient is weighted, and the weight factors include component replacement cost, downtime impact, and spare parts availability to generate a comprehensive impact score of component failure. Component replacement cost refers to the material cost and labor cost required to replace the component; downtime impact refers to the size of downtime loss caused by the component failure, including direct economic losses and indirect impacts; spare parts availability refers to the difficulty of obtaining spare parts for the component, including factors such as procurement cycle and number of suppliers. The specific method of weighted processing is: quantitatively score these three weight factors, usually using a 1-10 score system; then determine the weight coefficient of each factor, and the sum of the weight coefficients is 1; multiply the component failure risk coefficient by the weighted sum of the three weighted factors to obtain the component failure comprehensive impact score. This scoring method takes into account both the failure risk of the component itself and the comprehensive impact of the failure on production and maintenance, providing a scientific basis for the subsequent inspection priority sorting. According to the comprehensive impact score of component failure, the inspection urgency is divided into three levels of inspection: daily inspection items, key focus items, and emergency handling items. The classification standard is based on the threshold setting of the score, and the threshold is usually determined by the percentile method or expert experience method. For example, the scores can be arranged in ascending order, with the first 60% of the components classified as daily inspection items, 60%-90% of the components classified as key focus items, and the last 10% of the components classified as emergency treatment items. Or you can directly set the score threshold, such as scores below 50 points for daily inspection items, 50-80 points for key focus items, and above 80 points for emergency treatment items. Daily inspection items are items that require routine inspections during regular inspections and have a low inspection frequency; key focus items are items that require increased inspection frequency and detail; emergency treatment items are items that require priority inspection or preventive replacement. This hierarchical management method can reasonably allocate limited inspection resources and improve inspection efficiency.

[0050] Arrange components of different inspection levels in the order of production line layout to generate a priority sequence of inspection points for packaging equipment. The production line layout order refers to the order of material flow direction or equipment spatial position. The arrangement method is: group components according to the inspection level, with emergency processing items at the top, followed by key focus items, which are daily inspection items; then within each level, arrange them in the order of production line layout, from upstream to downstream, or from the feed end to the discharge end of the equipment; form a complete inspection point priority sequence list, including component name, location, inspection level, inspection points and other information. This sorting method takes into account both the urgency of the inspection and the rationality of the inspection path, which facilitates efficient execution by on-site inspection personnel. Taking the biscuit packaging line of a food packaging company as an example, by analyzing the equipment maintenance records in the past three years, the historical fault data of cutters, heat seal strips, transmission gears, and motor bearings were extracted. It was found that the average service life of the cutter was 800 hours, with a standard deviation of 120 hours, and the main fault types were wear and cracking; the average life of the heat seal strip was 600 hours, with a standard deviation of 90 hours, and the main faults were uneven temperature and adhesion; the average life of the transmission gear was 1500 hours, with a standard deviation of 200 hours, and the main faults were tooth surface wear and broken teeth; the average life of the motor bearing was 2000 hours, with a standard deviation of 300 hours, and the main faults were increased noise and overheating. These data were fitted to Weibull distribution to form the failure time distribution diagram of each component. Then, combined with the key component status evaluation table generated previously, it was found that the current state deviation of the cutter was 0.45, the heat seal strip was 0.28, the transmission gear was 0.33, and the motor bearing was 0.15. The proportional risk model was used to calculate the remaining life of the cutter to be 350 hours, the heat seal strip to be 400 hours, the transmission gear to be 950 hours, and the motor bearing to be 1700 hours. According to the analysis of the three recent condition monitoring data, the degradation rate of the cutter is 0.03 / hour, the heat seal is 0.02 / hour, the transmission gear is 0.01 / hour, and the motor bearing is 0.005 / hour. Based on the remaining life and degradation rate, the failure risk coefficient of each component is calculated: the cutter is 0.85, the heat seal is 0.65, the transmission gear is 0.40, and the motor bearing is 0.25. Further considering that the cutter replacement cost score is 3 (low cost), the downtime impact score is 8 (large impact), and the spare parts availability score is 2 (easy to obtain), the heat seal scores are 4, 7, and 3, the transmission gear scores are 6, 6, and 5, and the motor bearing scores are 5, 9, and 7, respectively, the comprehensive impact score of component failure is generated: the cutter is 82, the heat seal is 73, the transmission gear is 56, and the motor bearing is 62. According to the score, the cutter is classified as an emergency treatment item, the heat seal and motor bearing are key focus items, and the transmission gear is a daily inspection item. Arrange the components according to the order of production line layout (feeding, transmission, cutting, sealing, output) to form an inspection priority sequence: cutters in emergency processing items; motor bearings and heat sealing strips in key focus items; transmission gears in daily inspection items.Inspection personnel conduct inspections according to this sequence, which can timely identify potential failure risks and ensure stable operation of the equipment.

[0051] In a specific embodiment, the process of executing step S106 may specifically include the following steps: (1) For each component in the inspection point priority sequence, a dedicated inspection parameter set is extracted from the standard inspection specification library, including the cutter sharpness detection value, the heat seal temperature uniformity index, the transmission gear meshing clearance range, and the motor bearing vibration spectrum threshold; (2) Associating the detection parameter set with the abnormal threshold in the fault precursor feature library to construct a component status judgment standard table; (3) Set differentiated inspection cycles based on component failure risk factors and generate a component inspection time interval matrix; (4) Integrate the detection parameter set, judgment standard table and inspection time interval matrix into a component inspection operation card; (5) Schedule the time for component inspection work cards according to the production plan and maintenance resource allocation, and generate an inspection execution calendar; (6) Combine the component inspection work card with the inspection execution calendar to generate a preventive maintenance plan for packaging equipment.

[0052] Specifically, by querying the pre-established equipment inspection standard database, the professional inspection items and methods for each component are obtained. The standard inspection specification library is a collection of technical specifications and industry standards provided by equipment manufacturers, which contains inspection methods, judgment standards and operating procedures for various components. For the cutter, the sharpness detection value is extracted, that is, the quantitative index of the cutting ability of the cutter measured by the standard medium under the standard pressure; for the heat seal strip, the temperature uniformity index is extracted, that is, the maximum deviation value of the surface temperature distribution of the heat seal strip; for the transmission gear, the meshing clearance range is extracted, that is, the clearance measurement value between the meshing gears; for the motor bearing, the vibration spectrum threshold is extracted, that is, the upper limit of the vibration amplitude of each frequency band when the bearing is working normally. The detection parameter set is associated with the abnormal threshold in the fault precursor feature library to construct the component state judgment standard table, which is to pair the detection parameters extracted in the previous step with the corresponding abnormal feature threshold in the fault precursor feature library. The fault precursor feature library stores the typical change patterns of the equipment state parameters before different fault types occur, including the abnormal threshold of each parameter. The association method is to query the fault precursor feature library by comparison, extract the abnormal threshold corresponding to each detection parameter, and set the judgment standard. For example, when the sharpness of the cutter is lower than 80% of the standard value, it is determined to be in need of replacement; when the temperature uniformity deviation of the heat seal strip exceeds 5°C, it is determined to be in need of adjustment; when the meshing clearance of the transmission gear exceeds the standard range by 15%, it is determined to be in need of replacement; when the characteristic frequency amplitude in the vibration spectrum of the motor bearing exceeds the standard threshold, it is determined to be in need of maintenance. These judgment standards form a component status judgment standard table, which contains information such as detection parameters, normal range, warning range and danger range.

[0053] The process of setting differentiated inspection cycles based on component failure risk coefficients and generating component inspection time interval matrices is to set different inspection frequencies for different components based on the component failure risk coefficients calculated previously. Components with high failure risk coefficients require more frequent inspections, while components with low failure risk coefficients can reduce the inspection frequency. The specific setting method is to establish a mapping relationship between risk coefficients and inspection intervals, such as components with a risk coefficient of more than 0.8 are inspected once per shift, those with a risk coefficient of 0.5-0.8 are inspected once a day, those with a risk coefficient of 0.3-0.5 are inspected once a week, and those below 0.3 are inspected once a month. Considering the importance of components and historical failure modes at the same time, the mapping relationship is adjusted. The inspection time interval matrix finally formed is a two-dimensional table, with the rows as component names, the columns as time units (hours, days, weeks, etc.), and the cell values ​​as the number of inspections. Integrating the detection parameter set, the judgment standard table, and the inspection time interval matrix into a component inspection job card is to structure the data obtained in the first three steps to form a standardized document that is easy to execute on site. The inspection work card contains the following contents: basic information of the component (name, location, number, etc.); description of the detection parameter set and detection method; state judgment standard table; inspection cycle and time arrangement; guidance on handling measures when abnormalities are found; historical inspection record area, etc. Design dedicated work card templates for different components to ensure that inspectors can conduct inspections and judgments according to standard procedures.

[0054] According to the production plan and maintenance resource allocation, the component inspection work card is scheduled. The process of generating the inspection execution calendar is to coordinate the inspection work with the actual production plan to avoid the inspection activities affecting normal production. The specific method is: obtain the production plan for a period of time in the future (usually one month), including production time, downtime, product switching time, etc.; then match the maintenance personnel's schedule and skills; according to these constraints, assign specific execution time and person in charge to each inspection work card. Priority is given to arranging inspection items that affect production during the equipment downtime period, and inspection items that do not affect production can be arranged during the equipment operation period. The generated inspection execution calendar is usually displayed in a Gantt chart or calendar format, which intuitively displays the daily inspection task arrangement. Combining the component inspection work card with the inspection execution calendar to generate a preventive maintenance plan for packaged equipment is to integrate the work card and execution calendar formed in the first two steps into a complete maintenance management document. The preventive maintenance plan includes the following: an overview of the plan, including maintenance objectives, scope of application, division of responsibilities, etc.; an inspection execution calendar, which shows the time schedule for all inspection tasks; inspection work cards for each component as specific execution guidance; a maintenance resource requirement list, including personnel, tools, spare parts, etc.; maintenance effect evaluation standards and methods; plan adjustment and emergency response mechanisms, etc. This integrated process ensures the systematic and continuous nature of preventive maintenance activities and provides a clear action guide for equipment managers and inspectors.

[0055] Taking a beverage packaging production line as an example, for the cutter classified as an emergency treatment item, the cutter sharpness test standard was extracted from the standard test specification library, and it was stipulated that the reference material of standard thickness should be used to test the cutting performance under fixed pressure; for the heat seal strip in the key focus item, the temperature uniformity test standard was extracted, requiring the use of a thermal imager to scan the surface temperature distribution of the heat seal strip; for the motor bearing, the vibration spectrum test standard was extracted, requiring the use of a vibration analyzer to collect bearing vibration data and analyze the characteristic frequency. These test standards were associated with the abnormal thresholds in the fault precursor feature library, and it was determined that the cutter sharpness needs to be replaced when it is lower than 85% of the standard value, the heat seal strip needs to be adjusted when the temperature difference between each point exceeds 8°C, and the motor bearing needs to be repaired when the characteristic frequency vibration amplitude exceeds 0.7g. Based on the fault risk factor (cutter 0.85, heat seal strip 0.65, motor bearing 0.62), it is set that the cutter is inspected every 4 hours, the heat seal strip is inspected once per shift (8 hours), and the motor bearing is inspected once a day. This information is integrated into inspection cards for each component, and combined with the production plan (two-shift production from Monday to Friday, single-shift production on weekends, and equipment downtime for major maintenance on Wednesday of each month) and the maintenance staff schedule, a monthly inspection execution calendar is generated. Ultimately, all cards and calendars are integrated into a complete preventive maintenance plan, providing inspectors with detailed detection indicators, judgment criteria, and execution schedules to ensure the healthy operation of key components.

[0056] The above describes the packaging equipment inspection method in the embodiment of the present application. The following describes the packaging equipment inspection system in the embodiment of the present application. Figure 2 In the embodiment of the present application, an embodiment of the packaging equipment inspection system includes: The packaging process parameters are collected through the tension sensor, sealing temperature probe, and conveyor belt pulse encoder on the packaging equipment to form a comprehensive data set of packaging equipment working conditions; Based on the comprehensive data set of the working conditions, the abnormal consumption of packaging materials, the fluctuation of the sealing defect rate, and the uneven speed are extracted by spectrum analysis to generate the operating deviation index of the packaging equipment; Based on the operation deviation index, association rules are established by comparing historical data of product quality and equipment status parameters to obtain a feature library of precursors of packaging equipment failures; According to the fault precursor feature library, a time sequence comparison method is used to analyze the coordination of actions between various workstations of the packaging line, and a state evaluation table of key components of the packaging equipment is formed; According to the key component status evaluation table, combined with historical maintenance records, the failure probability of the cutter, heat seal strip, transmission gear, and motor bearing is calculated to generate a priority sequence of inspection points for the packaging equipment; According to the inspection point priority sequence, formulate an inspection operation guidance plan including detection parameters, judgment criteria, and inspection cycles to form a preventive maintenance plan for packaging equipment.

[0057] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0058] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0059] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0060] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0061] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0062] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0063] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A packaging equipment inspection method, characterized in that: The packaging equipment inspection method comprises: The packaging process parameters are collected through the tension sensor, sealing temperature probe, and conveyor belt pulse encoder on the packaging equipment to form a comprehensive data set of packaging equipment working conditions; Based on the comprehensive data set of the working conditions, the abnormal consumption of packaging materials, the fluctuation of the sealing defect rate, and the uneven speed are extracted by spectrum analysis to generate the operating deviation index of the packaging equipment; Based on the operation deviation index, association rules are established by comparing historical data of product quality and equipment status parameters to obtain a feature library of precursors of packaging equipment failures; According to the fault precursor feature library, a time sequence comparison method is used to analyze the coordination of actions between various workstations of the packaging line, and a state evaluation table of key components of the packaging equipment is formed; According to the key component status evaluation table, combined with historical maintenance records, the failure probability of the cutter, heat seal strip, transmission gear, and motor bearing is calculated to generate a priority sequence of inspection points for the packaging equipment; According to the inspection point priority sequence, formulate an inspection operation guidance plan including detection parameters, judgment criteria, and inspection cycles to form a preventive maintenance plan for packaging equipment.

2. The packaging equipment inspection method according to claim 1, characterized in that: The packaging process parameters are collected through the tension sensor, sealing temperature probe, and conveyor belt pulse encoder on the packaging equipment to form a comprehensive data set of packaging equipment working conditions, including: Multi-point sampling is performed on the instantaneous tension waveform of the tension sensor during the packaging material conveying process, the temperature curve of the sealing temperature probe during the heat sealing process, and the speed change signal of the conveyor belt pulse encoder; Divide the sampled signals into working units according to the operation cycle of the packaging equipment, and identify the key time nodes in the complete packaging cycle; Phase alignment of multi-sensor data based on key time nodes to eliminate signal transmission delay differences; The background interference of the phase-aligned signal is eliminated by wavelet denoising method to extract the effective working condition signal; Construct a three-dimensional working condition feature space and map the equipment operating status with tension-temperature-speed as the coordinate axes; Data point density analysis is performed in the three-dimensional working condition feature space to form a comprehensive data set of packaging equipment working conditions.

3. The packaging equipment inspection method according to claim 1, characterized in that: According to the comprehensive working condition data set, the spectrum analysis method is used to extract the abnormal consumption of packaging materials, the fluctuation of the sealing defect rate, and the uneven speed characteristics, and generate the packaging equipment operation deviation index, including: Multi-scale wavelet decomposition is performed on the tension signal in the comprehensive working condition data set to construct a tension fluctuation feature tree spectrum; Extract energy distribution abnormal area from tension fluctuation feature tree spectrum, calculate material tension peak deviation ratio, and form packaging material consumption abnormality identification fingerprint; Reconstruct the sealing temperature data sequence in phase space and draw the temperature trajectory attractor diagram; By calculating the Lyapunov index of the temperature trajectory attractor graph, the stability of the sealing system is quantified and a sealing defect rate fluctuation warning index is established; Nonlinear detrending analysis is used on the conveyor belt pulse sequence to extract the hidden patterns of small speed fluctuations; The hidden mode of tiny speed fluctuations is cross-correlated with the characteristic mode during standard operation to form a speed unevenness characteristic spectrum; Through the multi-dimensional feature space mapping algorithm, the abnormal identification fingerprint of packaging material consumption, the early warning index of sealing defect rate fluctuation and the speed unevenness feature spectrum are integrated into the packaging equipment operation deviation index.

4. The packaging equipment inspection method according to claim 1, characterized in that: Based on the operation deviation index, association rules are established by comparing the historical data of product quality and equipment status parameters to obtain a packaging equipment failure precursor feature library, including: Extract packaging integrity scores, seal strength test values, and appearance pass rate data from the product quality inspection database to build a product quality history matrix; Match the product quality history record matrix with the operation deviation index corresponding to the time in time series to form a dual-factor data chain of quality and equipment status; Conduct hysteresis analysis on the dual-factor data chain of quality and equipment status to determine the time window from the occurrence of operating deviation to the decline of product quality, and form a status-quality impact cycle diagram; Through the state-quality impact cycle diagram, we can group and distinguish the development characteristics of different fault types and draw the fault evolution trajectory curve; Extract key inflection points and threshold features from the fault evolution trajectory curve and mark early warning signal points; The early warning signal points are associated with specific fault types in historical maintenance records to obtain a packaging equipment fault precursor feature library.

5. The packaging equipment inspection method according to claim 1, characterized in that: According to the fault precursor feature library, the timing comparison method is used to analyze the coordination of actions between various workstations of the packaging line to form a key component status evaluation table of the packaging equipment, including: Collect the action timing signals of the feeding station, folding station, sealing station, cutting station and output station from the packaging equipment control system to construct the action time sequence of the packaging station; The action time series of the packaging station is synchronized with the standard time series template in the fault precursor feature library to generate a station action deviation map; Based on the workstation action deviation map, the action conversion delay values ​​between adjacent workstations are extracted to form the workstation connection abnormality measurement value; Decompose the abnormal measurement values ​​of workstation connection, identify the source of delay, and mark the key nodes of the drive chain between workstations; Analyze the changes in the motion characteristics of each key component through the key nodes of the drive chain between workstations, and calculate the deviation of the component's operating state; Compare the component operating status deviation with the component health threshold to form a key component status assessment table for packaging equipment.

6. The packaging equipment inspection method according to claim 1, characterized in that: The key component status evaluation table is used to calculate the failure probability of the cutter, heat seal strip, transmission gear, and motor bearing in combination with historical maintenance records, and a priority sequence of inspection points for packaging equipment is generated, including: Extract historical fault records of cutters, heat seals, transmission gears, and motor bearings from the equipment management system to build a component failure time distribution map; Compare the component failure time distribution diagram with the current state parameters in the key component state assessment table to calculate the component remaining life prediction value; Based on the predicted value of the remaining life of the component and the degradation rate of the component state, a component failure risk coefficient is formed; The component failure risk factor is weighted, with weight factors including component replacement cost, downtime impact, and spare parts availability, to generate a comprehensive component failure impact score; The inspection urgency is divided into three levels according to the comprehensive impact score of component failures: daily inspection items, key focus items, and emergency handling items; Arrange components of different inspection levels according to the production line layout order to generate a priority sequence of inspection points for packaging equipment.

7. The packaging equipment inspection method according to claim 1, characterized in that: According to the inspection point priority sequence, an inspection operation guidance plan including detection parameters, judgment criteria, and inspection cycle is formulated to form a preventive maintenance plan for packaging equipment, including: For each component in the inspection point priority sequence, a dedicated inspection parameter set is extracted from the standard inspection specification library, including the cutter sharpness detection value, heat seal temperature uniformity index, transmission gear meshing clearance range, and motor bearing vibration spectrum threshold; Associating the detection parameter set with the abnormal threshold in the fault precursor feature library to construct a component status judgment standard table; Set differentiated inspection cycles based on component failure risk factors and generate component inspection time interval matrix; Integrate the detection parameter set, judgment standard table and inspection time interval matrix into a component inspection operation card; According to the production plan and maintenance resource allocation, schedule the component inspection work cards and generate the inspection execution calendar; Combine component inspection job cards with the inspection execution calendar to generate a preventive maintenance plan for packaging equipment.

8. A packaging equipment inspection system, used to implement the packaging equipment inspection method according to any one of claims 1 to 7, characterized in that: The packaging equipment inspection system comprises: The acquisition module is used to collect packaging process parameters through the tension sensor, sealing temperature probe, and conveyor belt pulse encoder on the packaging equipment to form a comprehensive data set of packaging equipment working conditions; A generation module is used to extract the abnormal consumption of packaging materials, the fluctuation of sealing defect rate, and the uneven speed by spectrum analysis according to the comprehensive data set of working conditions, and generate the operation deviation index of the packaging equipment; Establishing a module for establishing association rules based on the operation deviation index by comparing the historical data of product quality and equipment status parameters to obtain a feature library of precursors of packaging equipment failures; An analysis module, used to analyze the coordination of actions between various workstations of the packaging line according to the fault precursor feature library by using a time sequence comparison method, and form a status evaluation table of key components of the packaging equipment; A calculation module is used to calculate the failure probability of the cutter, heat seal strip, transmission gear, and motor bearing according to the key component status evaluation table and in combination with historical maintenance records, and generate a priority sequence of inspection points for packaging equipment; The maintenance module is used to formulate an inspection operation guidance plan including detection parameters, judgment criteria, and inspection cycles according to the inspection point priority sequence, so as to form a preventive maintenance plan for packaging equipment.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and is characterized in that when the processor executes the computer program, the packaging equipment inspection method described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the processor is enabled to execute the packaging equipment inspection method according to any one of claims 1 to 7.

Images