Underwear production equipment operation state data processing method and system

Abstract

The invention relates to the technical field of data processing, in particular to an underwear production equipment operation state data processing method and system. The method comprises the following steps: acquiring a pulse signal of a rotary encoder, acquisition data of each sensor and an operation state of underwear production equipment; the rotary encoder pulse signals and the collected data are subjected to correlation marking, and all sensor data marked with pulse sequence numbers are obtained; obtaining all aligned sensor data according to all the sensor data marked with the pulse sequence numbers; according to the operation state of the underwear production equipment, pulse signal deviation is determined; obtaining all calibrated sensor data by using the pulse signal deviation; and matching all the calibrated sensor data with a preset causal association rule, determining each early warning component, and carrying out early warning prompt on each early warning component. The objective of the invention is to solve the problem that the quality of produced underwear products is poor due to the fact that operation state data cannot be accurately processed by an existing processing method.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, specifically to a method and system for processing operational status data of underwear production equipment. Background Technology

[0002] In the production workshop of seamless underwear, various sensors are used to acquire the operating status of the production equipment, such as the movement of knitting needles, yarn tension, and motor speed, to ensure the stable and efficient operation of the underwear production equipment. Currently, with the improvement of seamless underwear styles and production efficiency, some sensors inside the underwear production equipment have developed time-stamping discrepancies. For example, the data sampling time of the yarn tension sensor, the time delay of data transmission from the sensor to the main control system, and the inherent time of the internal signal processing of the sensor all result in time differences in status data between these discrepancies and the actual physical response speed and data reporting mechanism of high-frequency moving parts (such as the actuator cylinder of the pneumatic needle selector).

[0003] Existing operational status data processing methods suffer from small but cumulative relative time deviations when processing status data. These accumulated deviations obscure the causal relationships between events, making it difficult to accurately identify the initial event causing the anomaly and severely hindering data-driven early warning systems. Furthermore, the accumulated relative time deviations interfere with the precise timing of the initial event causing the anomaly, making data temporal consistency even more complex and unpredictable during the initial recovery and re-acceleration phase of the equipment. In other words, due to the combined effects of inherent sensor delays, data transmission delays, and recovery delays after automatic troubleshooting, existing operational status data processing methods cannot accurately align and determine the true millisecond-level temporal causal relationships between different sensor data when seamless underwear production equipment is operating at high load and high frequency. This significantly reduces the accuracy of warnings regarding impending needle wear, yarn breakage risks caused by feeder malfunctions, and servo motor overload precursors. There are instances where equipment is actually functioning normally but issues a fault warning, or equipment is about to fail but fails to issue a timely warning. Existing operational status data processing methods cannot accurately process operational data, which in turn affects the stability of underwear production and product quality, leading to reduced production efficiency and increased product scrap rates. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for processing operating status data of underwear production equipment, which solves the problem that existing operating status data processing methods cannot accurately process operating status data, thereby affecting the stability of underwear production and resulting in poor quality of the produced underwear products.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: a method for processing operating status data of underwear production equipment, comprising: Acquire the rotary encoder pulse signal of the main servo motor in the underwear production equipment, the data collected by each sensor in the underwear production equipment, and the operating status of the underwear production equipment; The rotary encoder pulse signal is associated and labeled with the data collected by each sensor to obtain all sensor data labeled with pulse sequence numbers; Based on all the sensor data marked with pulse sequence numbers, each sensor data is aligned with an event sequence to obtain all aligned sensor data; Based on the operating status of the underwear production equipment, determine the pulse signal deviation between the expected pulse signal and the rotary encoder pulse signal; Using the pulse signal deviation, all aligned sensor data are calibrated to obtain calibrated sensor data. Based on the matching of all the calibrated sensor data with the preset causal association rules, each warning component in the underwear production equipment is identified, and a warning prompt is given to each warning component.

[0006] Furthermore, the step of calibrating all aligned sensor data using the pulse signal deviation to obtain calibrated sensor data includes: Using the pulse signal deviation, all deviation data of the aligned sensor data with signal deviation are confirmed; Analyze all the deviation data to obtain a deviation data type that includes systematic drift or random noise; When the deviation data type is systematic drift, after confirming the pulse sequence offset, the aligned sensor data is calibrated to obtain all calibrated sensor data. When the deviation data type is random noise, the aligned sensor data is filtered to obtain all calibrated sensor data.

[0007] Further, the step of analyzing all the deviation data to obtain a deviation data type containing systematic drift or random noise includes: Confirm the moving average, trend slope, standard deviation, and instantaneous rate of change for each deviation data point over a continuous time period; The moving average and trend slope of each deviation data point over a continuous time period are determined to confirm the state of random noise in all deviation data. The standard deviation and instantaneous rate of change of each deviation data point over a continuous time period are determined to confirm the systematic drift state in all deviation data. Determine the superposition state of random noise state and systematic drift state under the same pulse number; Based on the random noise state, systematic drift state, and superposition state, a deviation data type containing systematic drift or random noise is obtained.

[0008] Furthermore, the step of determining the pulse signal deviation between the expected pulse signal and the rotary encoder pulse signal based on the operating status of the underwear production equipment includes: Based on the operating status of the underwear production equipment, determine the component response time and current operating parameters of the underwear production equipment; Based on the current operating parameters and historical recovery data, determine the expected response time of the component; The instantaneous response deviation is obtained by comparing the expected response time of the component with the actual response time of the component. Based on the instantaneous response deviation and the current operating parameters, the pulse signal deviation between the expected pulse signal and the rotary encoder pulse signal is determined.

[0009] Furthermore, the steps for determining the component response time and current operating parameters of the underwear production equipment based on its operating status include: Based on the operating status of the underwear production equipment, confirm the initial response time of each component of the underwear production equipment and the initial parameters of each operating condition; Determine the correlation coefficient between the initial response time of each component and the initial parameters of each operating condition; Based on each correlation coefficient, the initial response time of each component, and the initial parameters of each operating condition, the component response time and current operating condition parameters of the underwear production equipment are determined.

[0010] Furthermore, based on the operating status of the underwear production equipment, the steps for confirming the initial response time of each component of the underwear production equipment and the initial parameters of each operating condition include: Based on the operating status of the underwear production equipment, determine the current type of production material, the current parameter data for all operating conditions, and the current response time of all components; Based on the current type of production materials and the preset material library, determine the material adjustment weighting factor and time window length; By adjusting the material weighting factor and time window length, the current parameter data of all operating conditions and the current response time of all components are adjusted to obtain the initial response time of each component and the initial parameters of each operating condition of the underwear production equipment.

[0011] Furthermore, the step of determining each correlation coefficient between the initial response time of each component and the initial parameters of each operating condition includes: Based on the initial response time of each component and the initial parameters of each operating condition, the degree of equipment wear, environmental condition data, and initial coefficients of each correlation are confirmed. Based on the equipment wear level and the environmental condition data, confirm the coefficient correction parameters; Each initial correlation coefficient is adjusted using the aforementioned coefficient correction parameter to obtain each correlation coefficient.

[0012] Further, the step of associating and tagging the rotary encoder pulse signal with the acquired data of each sensor to obtain all sensor data tagged with pulse sequence numbers includes: The rotary encoder pulse signal is associated with the data collected by each sensor and the initial marking state of each sensor data is confirmed. The initial labeling state of each sensor data is verified to obtain all sensor data labeled with pulse sequence numbers.

[0013] Further, the step of aligning the event sequences of each sensor data point based on all the sensor data marked with pulse numbers to obtain all aligned sensor data includes: Based on all the sensor data marked with pulse sequence numbers, determine the pulse sequence number corresponding to each sensor data; The pulse sequence number corresponding to each sensor data is verified to obtain sensor data with a valid pulse sequence number. The event sequence of the qualified sensor data with pulse numbers is aligned to obtain all aligned sensor data.

[0014] The present invention also provides a data processing system for the operating status of underwear production equipment, the system comprising: The acquisition module is used to acquire the rotary encoder pulse signal of the main servo motor in the underwear production equipment, the data collected by each sensor in the underwear production equipment, and the operating status of the underwear production equipment. The marking module is used to associate and mark the rotary encoder pulse signal with the data collected by each sensor to obtain all sensor data marked with pulse sequence numbers; The alignment module is used to perform event sequence alignment on each sensor data according to all sensor data marked with pulse sequence numbers, so as to obtain all aligned sensor data. The confirmation module is used to determine the pulse signal deviation between the expected pulse signal and the rotary encoder pulse signal based on the operating status of the underwear production equipment. The calibration module is used to calibrate all aligned sensor data using the pulse signal deviation, thereby obtaining all calibrated sensor data. The early warning module is used to match all the calibrated sensor data with preset causal association rules to determine each early warning component in the underwear production equipment, and to provide early warning prompts for each early warning component.

[0015] Compared with the prior art, the data processing method and system for the operating status of underwear production equipment of the present invention has the following advantages: This invention achieves initial time synchronization of sensor data by acquiring the rotary encoder pulse signal of the main servo motor, sensor data, and equipment operating status, and associating and marking the pulse signal with the sensor data. Next, event sequence alignment is performed on the marked sensor data to ensure relative consistency of different sensor data along the time axis. Then, based on the equipment operating status, the deviation between the expected pulse signal and the actual rotary encoder pulse signal is dynamically determined, and this deviation is used to calibrate the aligned sensor data. This effectively compensates for small but continuously accumulating time deviations caused by inherent sensor delays, data transmission delays, and recovery delays after automatic troubleshooting, resulting in highly accurate calibrated sensor data. Finally, by matching the calibrated data with preset causal association rules, potential warning components in the underwear production equipment can be accurately identified, and timely warnings can be issued. This improves the accuracy of processing operating status data, significantly reduces false alarms and missed alarms in underwear production equipment, and ensures the stability and quality of underwear production. Attached Figure Description

[0016] To more clearly illustrate the specific embodiments of the present invention, the accompanying drawings used in the specific embodiments will be briefly described below. In all the drawings, the elements or parts are not necessarily drawn to scale.

[0017] Figure 1 This is a flowchart of a method for processing operating status data of underwear production equipment according to the present invention.

[0018] Figure 2 This is a structural block diagram of an underwear production equipment operation status data processing system according to the present invention.

[0019] In the diagram: 210, Acquisition module; 220, Marking module; 230, Alignment module; 240, Confirmation module; 250, Calibration module; 260, Early warning module.

[0020] The implementation and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] The following drawings disclose several embodiments of the present invention. For clarity, many practical details will be described in the following description. However, it should be understood that these practical details are not intended to limit the invention. That is, in some embodiments of the invention, these practical details are not essential. Furthermore, for the sake of simplicity, some conventional structures and components will be shown in the drawings in a simple schematic manner.

[0022] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0023] Furthermore, in this invention, the use of terms such as "first" and "second" is for descriptive purposes only and does not specifically refer to any order or sequence, nor is it intended to limit the invention. They are merely used to distinguish components or operations described using the same technical terms, and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but only if they are feasible for those skilled in the art. If a combination of technical solutions is contradictory or impossible to implement, such a combination should be considered nonexistent and not within the scope of protection claimed by this invention.

[0024] In the production of seamless underwear, the efficient and stable operation of production equipment ensures both quality and production efficiency. However, existing operational status data processing methods, when faced with high-frequency and rapidly changing production modes, suffer from slight misalignments in data time stamps due to differences in data acquisition, transmission, and internal processing speeds among different sensors. These methods struggle to accurately process operational status data, thus failing to precisely reflect the true sequence of events. This affects the accuracy of early warnings, leading to false alarms or missed alarms for underwear production equipment, ultimately reducing the stability of underwear production and the quality of the underwear.

[0025] To further understand the content, features, and effects of this invention, the following embodiments are provided, and detailed descriptions are given below in conjunction with the accompanying drawings: Please see Figure 1 This invention provides a method for processing operating status data of underwear production equipment, comprising the following steps: S100: Acquire the rotary encoder pulse signal of the main servo motor in the lingerie production equipment, the data collected by each sensor in the lingerie production equipment, and the operating status of the lingerie production equipment. Lingerie production equipment typically refers to various mechanical equipment used to produce seamless lingerie, such as circular knitting machines and sewing machines. The main servo motor is the motor that drives the core moving parts of the lingerie production equipment; its rotary encoder pulse signal reflects the precise motion trajectory and speed of the equipment. Sensors are devices used to collect equipment operating status data, such as optical sensors for monitoring needle movement, piezoelectric tension sensors for monitoring yarn tension, and rotary encoders for monitoring motor speed. Collected data refers to the raw data collected by sensors at a specific point in time or within a time period. The operating status of the lingerie production equipment refers to comprehensive information such as the current production mode, production speed, material type, and environmental conditions. The rotary encoder pulse signal in this step can be obtained by directly connecting to the encoder interface of the main servo motor. This interface typically outputs high-frequency digital pulse signals, representing the angle or displacement of the motor rotation. Sensor data can be read directly from the sensors via their respective communication interfaces (such as Modbus, Ethernet / IP, or CAN bus). This data may include analog or digital quantities such as voltage, current, frequency, temperature, and pressure. The operating status of the lingerie production equipment can be obtained through the equipment's PLC (Programmable Logic Controller) or SCADA (Supervisory and Data Acquisition) system, which typically records parameters such as the equipment's current production mode, production speed, material type, ambient temperature, and humidity.

[0026] S200: Associate the rotary encoder pulse signal with the data acquired by each sensor to obtain all sensor data marked with pulse sequence numbers. The pulse sequence number is a sequence identifier generated based on the rotary encoder pulse signal, used to align and associate different sensor data. This step can assign a unique pulse sequence number to each rotary encoder pulse signal. Then, when each sensor acquires data, record the pulse sequence number corresponding to the current main servo motor and use this pulse sequence number as the association marker for that sensor data. This can be achieved by synchronously reading the pulse counter value during data acquisition, or by using timestamp matching to approximately match the timestamp of the sensor data with the timestamp of the pulse signal, and then assigning the nearest pulse sequence number.

[0027] S300. Based on all the sensor data marked with pulse sequence numbers, perform event sequence alignment on each sensor data to obtain all aligned sensor data. Event sequence alignment refers to precisely aligning data collected by different sensors at different time points according to their corresponding pulse sequence numbers to reflect the actual order of events. In this step, after obtaining the sensor data marked with pulse sequence numbers, the collected data from different sensors can be reordered and aligned according to the pulse sequence numbers. If multiple sensor data correspond to the same pulse sequence number, they can be further sorted according to their respective internal timestamps or preset priorities. If expected data from certain sensors is missing under a certain pulse sequence number, interpolation processing or marking it as missing can be performed.

[0028] S400. Based on the operating status of the underwear production equipment, determine the pulse signal deviation between the expected pulse signal and the rotary encoder pulse signal. The pulse signal deviation refers to the difference between the expected pulse signal and the actual rotary encoder pulse signal, reflecting anomalies or drifts in equipment operation. This step can search for the corresponding expected pulse signal sequence from a preset equipment performance model or historical data based on the current operating status of the underwear production equipment (such as production speed, material type, and product model). Then, compare the actual acquired rotary encoder pulse signal with the expected pulse signal sequence one by one to obtain the difference, thus obtaining the pulse signal deviation. The pulse signal deviation can be a time offset or a difference in the number of pulses.

[0029] S500. Using the pulse signal deviation, calibrate all aligned sensor data to obtain calibrated sensor data. Calibration involves correcting the sensor data using the pulse signal deviation to eliminate time misalignment and systematic errors. In this step, the pulse signal deviation manifests as a time offset, so the timestamps of all aligned sensor data can be adjusted accordingly to match the calibrated pulse signal time. If the deviation manifests as a difference in the number of pulses, it may be necessary to resample or interpolate the sensor data to match the calibrated pulse sequence.

[0030] S600. Match all calibrated sensor data with preset causal association rules to determine each warning component in the underwear production equipment, and issue a warning prompt to each warning component. The preset causal association rules are a pre-established knowledge base or model describing the causal relationship between equipment component failures and sensor data anomalies. A warning component refers to an equipment component identified as having a potential failure risk based on the matching results. A warning prompt is an alert issued to the operator or control system, indicating a potential failure risk. In this step, the preset causal association rules define the association between specific sensor data patterns (e.g., a sensor data continuously exceeding a threshold at a certain pulse number, or an abnormal temporal relationship between multiple sensor data) and specific equipment component failures (e.g., needle wear, yarn feeder malfunction, and servo motor overload). The calibrated sensor data is input into this rule base or model for matching. Once a pattern matching the warning conditions is found, the corresponding warning component is determined, and a warning prompt is issued to the operator, for example, through audible and visual alarms, display screen information prompts, or by sending SMS or email.

[0031] In this embodiment, the acquisition of rotary encoder pulse signals from the main servo motor, data collected from various sensors, and the equipment's operating status provides a foundation for subsequent data processing. The rotary encoder pulse signal, serving as a precise reference for equipment movement, is crucial for achieving high-precision data alignment. Subsequently, the rotary encoder pulse signal is associated with and tagged with the data collected from each sensor, ensuring that each sensor data can be traced back to its corresponding equipment movement state, resolving the initial time misalignment between different sensor data on the timeline. Then, based on the sensor data tagged with pulse sequence numbers, event sequence alignment is performed on each sensor data. This eliminates relative time deviations caused by factors such as sensor sampling frequency and transmission delay, enabling precise alignment of events from different sensors within the same equipment movement cycle, thus laying the foundation for subsequent causal relationship analysis. Finally, based on the operating status of the underwear production equipment, the pulse signal deviation between the expected pulse signal and the rotary encoder pulse signal is determined. By comparing the differences between the actual and expected operation of the equipment, potential systematic drift or random noise in the equipment is identified. Subsequently, using the determined pulse signal deviation, all aligned sensor data are calibrated, effectively correcting the timestamps or values ​​of the sensor data to more accurately reflect the actual operating status of the equipment. Finally, all calibrated sensor data are matched with preset causal association rules to identify each warning component in the lingerie production equipment, and a warning message is issued for each component. Through precisely calibrated data, potential fault modes and causal relationships can be more accurately identified, enabling early and accurate warnings for problems such as needle wear, yarn feeder malfunctions, and servo motor overload, significantly improving equipment reliability and production efficiency. This invention, by introducing pulse signal deviation calibration, can identify and correct dynamic deviations caused by changes in equipment operating status, thereby significantly improving the accuracy of data analysis. This effectively reduces production line downtime, decreases the scrap rate in lingerie production, and improves both production efficiency and quality in lingerie manufacturing.

[0032] In some embodiments of this application described above, the step of calibrating all aligned sensor data using the pulse signal deviation to obtain calibrated sensor data includes: Using the pulse signal deviation, all deviation data of the aligned sensor data with signal deviation are confirmed. This step refers to identifying all sensor data points with deviations by comparing the expected pulse signal with the actual rotary encoder pulse signal.

[0033] Analyze all the deviation data to obtain the deviation data type containing systematic drift or random noise. This step aims to perform pattern recognition on the identified deviation data, distinguishing whether it exhibits long-term, stable systematic deviation (systematic drift) or short-term, irregular random fluctuations (random noise). Specifically, this can be achieved through statistical analysis methods, such as evaluating the mean, variance, or trend of the deviation data.

[0034] When the deviation data type is systematic drift, after confirming the pulse sequence offset, the aligned sensor data is calibrated to obtain calibrated sensor data. Specifically, systematic drift usually manifests as an overall data offset or trend change. The calibration process eliminates systematic deviation by determining a fixed or time-varying pulse sequence offset and shifting or adjusting the sensor data as a whole.

[0035] When the deviation data type is random noise, the aligned sensor data is filtered to obtain calibrated sensor data. Specifically, random noise manifests as irregular fluctuations in the data, typically without a clear trend. To address random noise, the calibration process employs filtering techniques, such as moving average filtering, Gaussian filtering, or Kalman filtering, to smooth the data and reduce the impact of noise on data accuracy.

[0036] Specifically, after prolonged operation, the rotary encoder pulse signal of the main servo motor in the lingerie production equipment exhibits a persistently and slowly increasing deviation from the expected pulse signal, which is identified as systematic drift. Simultaneously, due to electromagnetic interference in the workshop environment, occasional instantaneous high-frequency fluctuations appear in the sensor data, identified as random noise. This invention first uses pulse signal deviation to confirm all deviation data. Then, by analyzing the statistical characteristics of the deviation data, such as calculating moving averages and trend slopes, it identifies persistent deviations as systematic drift and instantaneous fluctuations as random noise. For systematic drift, the pulse sequence offset is determined; for example, if it is found that for every 1000 pulses, the actual pulse lags behind by one pulse sequence number, the subsequent sensor data is calibrated by shifting the pulse sequence number forward accordingly. For random noise, an algorithm such as a moving average filter is used to smooth the affected sensor data to eliminate instantaneous fluctuations. Through this differentiated processing, the final calibrated sensor data more accurately reflects the true operating status of the equipment, effectively avoiding false alarms or missed warnings caused by data deviations.

[0037] This embodiment identifies all sensor data with deviations by utilizing pulse signal bias and further analyzes these biased data, classifying them into two main types: systematic drift and random noise. Systematic drift is typically caused by long-term factors such as equipment wear, environmental changes, or sensor aging, manifesting as an overall data offset or trend, requiring overall adjustment by confirming the pulse sequence offset. Random noise, on the other hand, is mostly instantaneous interference or measurement error, manifesting as irregular fluctuations in the data, and is more suitable for smoothing through filtering. By employing customized calibration strategies for different types of deviations, errors in the data can be eliminated more accurately, avoiding undercalibration or overcalibration problems that may arise from a single calibration method, thereby significantly improving the accuracy and reliability of sensor data.

[0038] In some embodiments of this application described above, the step of analyzing all the deviation data to obtain a deviation data type containing systematic drift or random noise includes: The moving average, trend slope, standard deviation, and instantaneous rate of change for each deviation data point over a continuous time period are determined. Deviation data refers to all aligned sensor data with signal deviations, confirmed using pulse signal deviation analysis. A continuous time period can be understood as a continuous time window used to analyze data characteristics; its length can be adjusted according to the actual application scenario and data characteristics. Specifically, the moving average is used to smooth the data to reflect the short-term trend within a specific time window; the trend slope quantifies the direction and strength of the data's trend over time; for example, a positive slope indicates an upward trend, and a negative slope indicates a downward trend. The standard deviation is a statistic that measures the volatility or dispersion of data; a larger standard deviation usually indicates significant data fluctuations; the instantaneous rate of change reflects the speed of data change over a very short period and can be used to capture sudden changes or anomalies in the data.

[0039] The moving average and trend slope of each deviation data point over a continuous time period are assessed to identify the state of random noise in all deviation data. Random noise typically manifests as irregular fluctuations in the moving average and trend slope within a small range, lacking a clear and continuous direction.

[0040] The standard deviation and instantaneous rate of change of each deviation data point over a continuous time period are assessed to identify the systematic drift state in all deviation data. Systematic drift is typically characterized by a relatively small standard deviation, but a trend slope that continuously changes in a certain direction, or an instantaneous rate of change that continuously accumulates within a certain range, resulting in a slow, directional shift in the overall data.

[0041] The superposition state of random noise and systematic drift under the same pulse number needs to be determined. Specifically, at a certain moment or under a certain pulse number, the deviation data may be affected by both random noise and systematic drift simultaneously, requiring a comprehensive assessment of the coexistence of these two states.

[0042] Based on the random noise state, systematic drift state, and superposition state, a deviation data type containing systematic drift or random noise is obtained. This provides an accurate classification basis for subsequent calibration processing.

[0043] This embodiment employs multi-dimensional statistical analysis of deviation data, including moving average, trend slope, standard deviation, and instantaneous rate of change, to more comprehensively and accurately capture its inherent characteristics. Moving average and trend slope help identify long-term or short-term trends in the data, which is particularly crucial for judging systematic drift; while standard deviation and instantaneous rate of change effectively reflect the volatility and abrupt changes in the data, and are of great significance for identifying random noise. By comprehensively judging these indicators and considering their superposition, the limitations of judging with a single indicator can be avoided, thereby accurately distinguishing between systematic drift and random noise.

[0044] In some embodiments of this application described above, the step of determining the pulse signal deviation between the expected pulse signal and the rotary encoder pulse signal based on the operating status of the underwear production equipment includes: Based on the operating status of the lingerie production equipment, the component response time and current operating parameters of the equipment are determined. Specifically, the component response time refers to the time required for each component in the lingerie production equipment to complete its corresponding action after receiving an instruction. This time is affected by various factors, such as the wear and tear of the components, lubrication status, ambient temperature, and the currently executed production task. Current operating parameters refer to the various process and environmental parameters of the lingerie production equipment under its current operating state, such as production speed, material type, processing pressure, and ambient humidity.

[0045] Based on the current operating parameters and historical recovery data, the expected response time of the component is determined. The historical recovery data is a collection of data accumulated during the long-term operation of the system regarding component response time, operating parameters, and equipment performance. This data, after processing and analysis, is used to establish a predictive model for the component response time.

[0046] The instantaneous response deviation is obtained by comparing the expected response time of the component with its actual response time. The expected response time is derived from model prediction or experience based on current operating parameters and historical recovery data, representing the response time the component should achieve under ideal or normal operating conditions. The instantaneous response deviation is the difference between the actual response time and the expected response time of the component; this deviation directly reflects whether the component's current operating state is normal.

[0047] Based on the instantaneous response deviation and the current operating parameters, the pulse signal deviation between the expected pulse signal and the rotary encoder pulse signal is determined.

[0048] Specifically, when producing underwear made of a specific material, the underwear production equipment continuously acquires pulse signals from the rotary encoder of the main servo motor. Simultaneously, multiple sensors within the equipment collect data such as temperature, pressure, and vibration. Based on the current operating status of the underwear production equipment, including the type of material being produced, production speed, and ambient temperature, the actual response time and current operating parameters of key components (such as the sewing head and feeding mechanism) are acquired in real time. For example, the actual time from receiving a command to completing one sewing action by the sewing head, as well as the current sewing speed and thread tension. Then, using component response data stored in a historical database for that material type, sewing speed, and thread tension, combined with the current operating parameters, the expected response time of the sewing head under the current conditions is predicted. Subsequently, the actual response time is compared with the expected response time to determine the instantaneous response deviation. If the actual response time is significantly longer than the expected response time, it indicates that the sewing head may be worn or jammed. Finally, by comprehensively considering this instantaneous response deviation and operating parameters such as the current sewing speed, the pulse signal deviation between the expected pulse signal of the main servo motor and the actual rotary encoder pulse signal can be determined. This deviation value will be used for subsequent sensor data calibration to ensure that all sensor data are accurately aligned with the motion cycle of the main servo motor, thereby improving the accuracy of equipment operation status monitoring.

[0049] This embodiment obtains the component response time and current operating parameters of the underwear production equipment based on its operating status, providing real-time foundational data for subsequent deviation analysis. Furthermore, by combining the current operating parameters and historical recovery data, the expected response time of the components under current conditions can be accurately predicted. By comparing the actual component response time with the predicted expected response time, the instantaneous response deviation can be accurately calculated, directly reflecting the real-time changes in component performance. Finally, based on this instantaneous response deviation and the current operating parameters, the pulse signal deviation between the expected pulse signal and the rotary encoder pulse signal can be comprehensively determined, making the deviation determination more closely reflect the actual operating conditions of the equipment.

[0050] In some embodiments of this application described above, the step of determining the component response time and current operating parameters of the underwear production equipment based on its operating status includes: Based on the operating status of the lingerie production equipment, confirm the initial response time of each component and the initial parameters for each operating condition. This step refers to identifying and recording the inherent response characteristics of each component and the baseline values ​​of various operating parameters in the lingerie production equipment during the initial stage of equipment operation or under standard operating conditions. The initial parameters can be obtained from the equipment's factory settings, historical operating data, design specifications, or through specialized calibration tests, with the aim of establishing a stable reference baseline.

[0051] Determine the correlation coefficient between the initial response time of each component and the initial parameters for each operating condition. This step aims to analyze and quantify the interrelationships between the initial response times of different components and the initial parameters for different operating conditions. For example, the response time of actuators (such as the feeding mechanism) may change as production speed (operating condition parameters) increases. Correlation coefficients are obtained through statistical analysis of historical data, controlled experiments, or modeling using expert experience, with the aim of revealing the inherent coupling mechanisms in equipment operation.

[0052] Based on each correlation coefficient, the initial response time of each component, and the initial parameters of each operating condition, the component response time and current operating condition parameters of the lingerie production equipment are determined. Specifically, this step involves using the confirmed initial parameters and their correlation coefficients, combined with the equipment's current actual operating status, to dynamically derive the actual response time of each component under the current operating conditions and the precise values ​​of various operating condition parameters. For example, if the operating condition parameters deviate from the initial values, the response time of the affected components can be predicted and adjusted based on the corresponding correlation coefficients, thereby obtaining more realistic component response times and current operating condition parameters.

[0053] Specifically, in lingerie production equipment, there is a correlation between the response time of the sewing machine's needle bar component and the production line's feed speed parameters. First, the initial response time of the needle bar component is confirmed to be 50 milliseconds, and the initial feed speed parameter is 1000 mm / s. Through analysis of historical data, a correlation coefficient is determined between the needle bar component's response time and the feed speed; for example, for every 100 mm / s increase in feed speed, the needle bar component's response time decreases by 2 milliseconds. When the feed speed changes to 1200 mm / s during actual equipment operation, this correlation coefficient is used to adjust the needle bar component's response time to 46 milliseconds. This allows for the dynamic and precise determination of the needle bar component's response time based on the current actual operating parameters, providing more accurate input for subsequent pulse signal deviation calculations.

[0054] This embodiment establishes baselines for component initial response times and initial operating parameters, and further quantifies the correlation between them, enabling a more comprehensive and in-depth understanding of the dynamic behavior of lingerie production equipment under different operating conditions. Due to the precise modeling of the inherent correlations, during actual equipment operation, the component response time can be dynamically and accurately corrected based on current operating parameters and known correlations, thus avoiding errors that may arise from relying solely on static initial values.

[0055] In some embodiments of this application described above, the steps for determining the initial response time of each component of the underwear production equipment and the initial parameters of each operating condition based on the operating status of the underwear production equipment include: Based on the operating status of the underwear production equipment, determine the current production material type, current parameter data for all operating conditions, and current response time of all components. The current production material type refers to the type of raw material currently being processed by the underwear production equipment, such as cotton, silk, and synthetic fibers. The current parameter data for all operating conditions can be understood as the real-time measured values ​​related to various process conditions under the current production state, such as temperature, pressure, speed, and tension. The current response time of all components refers to the actual response time of each key component of the equipment under the current operating conditions, such as the start-up time of the main servo motor and the sampling delay of sensors.

[0056] Based on the current production material type and the preset material library, the material adjustment weighting factor and time window length are determined. The preset material library is a database storing different material properties and their corresponding adjustment parameters, including material adjustment weighting factors and time window lengths for each material. The material adjustment weighting factor is a coefficient used to quantify the impact of different materials on equipment operating parameters and response time; its purpose is to weight and correct the original data to adapt to the processing characteristics of specific materials. The time window length defines the time range of historical or real-time data to be considered when adjusting data, aiming to ensure the timeliness and effectiveness of adjustments and avoid errors introduced by data lag or obsolescence.

[0057] By adjusting the material weighting factor and time window length, the current parameter data and current response time of all components under all operating conditions are adjusted to obtain the initial response time of each component and the initial parameters for each operating condition of the lingerie production equipment. This step aims to eliminate or reduce data bias caused by differences in material type, so that the original current parameter data and current response time can more accurately reflect the true state of the equipment under specific material processing conditions. Through adjustment, a more accurate initial response time for each component and the initial parameters for each operating condition of the lingerie production equipment are finally obtained.

[0058] Specifically, when processing new elastic fiber materials, the underwear production equipment identifies the current material type as elastic fiber based on its operating status. Simultaneously, it acquires current parameter data for all operating conditions (e.g., sewing speed, tension, and heating temperature) and the current response time of all components (e.g., the response time of the feeding mechanism and the needle movement). Next, it queries a preset material library and, based on the elastic fiber material type, obtains the corresponding material adjustment weighting factor (e.g., a tension parameter weighting factor of 1.2 and a heating temperature weighting factor of 0.9) and time window length (e.g., 5 seconds). Subsequently, using the adjustment weighting factor and time window length, it adjusts all acquired operating condition parameter data and the current response time of all components. For example, the originally measured tension parameter data is multiplied by 1.2 to reflect the higher tension requirements of elastic fibers; the originally measured heating temperature data is multiplied by 0.9 to accommodate the temperature sensitivity of elastic fibers. Simultaneously, the data trend within the last 5 seconds is considered during the adjustment process. This ensures that the initial response time of each component of the underwear production equipment and the initial parameters of each operating condition will more accurately reflect the actual operating conditions when processing elastic fibers, thus providing a more reliable basis for subsequent pulse signal deviation calculation and equipment early warning.

[0059] This embodiment refines the original operating condition parameters and component response times by introducing the current production material type and combining it with material adjustment weighting factors and time window lengths from a preset material library. By obtaining targeted adjustment parameters from a preset material library based on the current production material type and applying them to real-time data, this invention effectively compensates for the impact of material differences. The resulting initial response times for each component and initial operating condition parameters more accurately reflect the actual behavior of the equipment under specific material processing conditions, providing a more solid and precise foundation for subsequently determining the component response times and current operating condition parameters of the underwear production equipment.

[0060] In some embodiments of this application described above, the step of determining each correlation coefficient between the initial response time of each component and the initial parameters of each operating condition includes: Based on the initial response time of each component and the initial parameters of each operating condition, the degree of equipment wear, environmental condition data, and initial correlation coefficients are determined. The degree of equipment wear refers to the physical wear or performance degradation of each component in the lingerie production equipment during use, such as bearing wear and increased clearance in transmission components. This can be assessed through equipment operating time, maintenance records, vibration analysis, or visual inspection. Environmental condition data refers to the various physical parameters of the environment in which the lingerie production equipment operates, such as workshop temperature, humidity, and dust concentration, which can be collected in real time using environmental sensors. Each initial correlation coefficient refers to the preset correlation strength or trend between the initial response time of each component and the initial parameters of each operating condition under ideal or standard conditions.

[0061] Based on the equipment wear level and environmental condition data, coefficient correction parameters are determined. Specifically, coefficient correction parameters are factors used to dynamically adjust the initial correlation coefficients, aiming to compensate for the impact of equipment wear and environmental changes on the relationship between component response characteristics and operating parameters. For example, when the equipment wear level is high, the coefficient correction parameters may increase the correlation between the response time of a component and specific operating parameters to reflect the response hysteresis or instability caused by wear; when the ambient temperature is too high, the coefficient correction parameters may adjust the mapping relationship between sensor data and actual physical quantities.

[0062] Each initial correlation coefficient is adjusted using the aforementioned coefficient correction parameters to obtain a single correlation coefficient. Specifically, the adjustment process can be multiplicative correction, additive correction, or other more complex nonlinear correction models, with the aim of enabling the correlation coefficients to more accurately reflect the true correlation relationship under the current equipment status and environmental conditions.

[0063] This embodiment incorporates equipment wear and environmental condition data, and uses this dynamic information to confirm and correct parameters, thereby adjusting each initial correlation coefficient. Equipment wear directly reflects the physical state of components, and its changes directly affect the response characteristics of components; environmental condition data reflects the impact of the external environment on equipment operation and sensor measurements. By incorporating these real-time changing factors into the correlation coefficient determination process, each obtained correlation coefficient is no longer static, but dynamically adaptable to equipment aging and environmental changes, thus more accurately representing the true correlation between the initial response time of each component and the initial parameters of each operating condition.

[0064] In some embodiments of this application described above, the step of associating and marking the rotary encoder pulse signal with the data collected by each sensor to obtain all sensor data marked with pulse sequence numbers includes: The rotary encoder pulse signal is associated and tagged with the data collected by each sensor to confirm the initial tagging state of each sensor data. Specifically, this step involves, after acquiring the rotary encoder pulse signal of the main servo motor in the underwear production equipment and the data collected by each sensor in the equipment, performing preliminary matching and binding of each sensor data with the corresponding rotary encoder pulse signal according to a preset association logic, such as timestamp-based synchronous matching or event sequence-based sequential matching. Each sensor data is assigned an initial pulse sequence number tag to establish a preliminary correspondence between the sensor data and the equipment's motion state.

[0065] The initial labeling status of each sensor data point is verified to obtain all sensor data labeled with pulse sequence numbers. This step involves checking the consistency, completeness, and accuracy of the initially associated labeling status after initial labeling. Specifically, the initial labeling status can be verified in multiple dimensions, such as checking for anomalies like missing pulse sequence numbers, duplicate labeling, severe mismatches between sensor data and pulse signal timestamps, or discrepancies in the logical order of sensor data and pulse signals. Through verification, inaccurate initial labeling can be corrected or eliminated, ensuring that the final sensor data labeled with pulse sequence numbers is reliable and of high quality, thus laying a solid foundation for subsequent data alignment and calibration processes.

[0066] This embodiment effectively avoids inaccurate labeling caused by initial association errors or abnormal data transmission by confirming the initial labeling state of each sensor data and then verifying that initial labeling state. The introduction of the verification process allows for quality control of the initial association results when associating the rotary encoder pulse signal with the data collected by each sensor, thereby ensuring that the pulse sequence number carried by each sensor data is accurate.

[0067] In some embodiments of this application described above, the step of aligning each sensor data point with an event sequence based on all sensor data marked with pulse numbers to obtain all aligned sensor data includes: Based on all the sensor data marked with pulse sequence numbers, determine the pulse sequence number corresponding to each sensor data point. Determining the pulse sequence number for each sensor data point means identifying and extracting the specific pulse sequence number associated with each sensor data point after it has been marked with a pulse sequence number. This is typically achieved by parsing the data structure or searching a pre-defined association mapping, with the aim of providing a basic event timestamp for subsequent data verification and alignment operations.

[0068] The pulse sequence number corresponding to each sensor data point is verified to obtain valid sensor data with pulse sequence numbers. Specifically, the verification process may include, but is not limited to, checking the validity, continuity, and consistency with the timestamp of the pulse sequence number. For example, it may check whether the pulse sequence number is within a reasonable range, whether there are jumps or repetitions, or whether there is a significant deviation from the sensor data acquisition time. Through this verification, abnormal or incorrectly labeled sensor data can be effectively identified and eliminated, thereby ensuring the accuracy and reliability of subsequent data processing.

[0069] The event sequence alignment is performed on the verified sensor data with pulse numbers to obtain all aligned sensor data. Event sequence alignment refers to synchronizing and sorting data collected by different sensors at different times based on their common pulse numbers. This ensures that all sensor data related to a specific production event are logically aligned, forming a unified event sequence and providing a consistent data foundation for subsequent deviation analysis and calibration. For example, timestamp interpolation, nearest neighbor matching, or pulse number-based synchronization algorithms can be used to achieve this.

[0070] This embodiment first determines the pulse sequence number corresponding to each sensor data point, laying the foundation for subsequent data processing. Then, rigorous verification of the pulse sequence numbers effectively identifies and eliminates erroneous data that may occur during acquisition, transmission, or tagging, thus ensuring the purity and reliability of the data source. Because the verified data has higher accuracy, subsequent event sequence alignment can more accurately synchronize sensor data from different sources to a common production event, forming a logically consistent and temporally accurate data sequence. This step-by-step processing method with verification mechanisms ensures that the operational status data of the underwear production equipment is processed before entering subsequent analysis and calibration stages, improving the data quality of the operational status data.

[0071] Based on any of the above embodiments, a method for processing operating status data of underwear production equipment is provided. Figure 2 The present invention also provides a data processing system for the operating status of underwear production equipment, the system comprising an acquisition module 210, a marking module 220, an alignment module 230, a confirmation module 240, a calibration module 250, and an early warning module 260.

[0072] The acquisition module 210 is used to acquire the rotary encoder pulse signal of the main servo motor in the underwear production equipment, the data collected by each sensor in the underwear production equipment, and the operating status of the underwear production equipment.

[0073] The marking module 220 is used to associate and mark the rotary encoder pulse signal with the data collected by each sensor to obtain all sensor data marked with pulse sequence numbers.

[0074] The alignment module 230 is used to perform event sequence alignment on each sensor data according to all sensor data marked with pulse sequence numbers, so as to obtain all aligned sensor data.

[0075] The confirmation module 240 is used to determine the pulse signal deviation between the expected pulse signal and the rotary encoder pulse signal based on the operating status of the underwear production equipment.

[0076] The calibration module 250 is used to calibrate all aligned sensor data using the pulse signal deviation to obtain calibrated sensor data.

[0077] The early warning module 260 is used to match all the calibrated sensor data with preset causal association rules to determine each early warning component in the underwear production equipment, and to provide early warning prompts for each early warning component.

[0078] In this embodiment, the acquisition module 210 acquires the rotary encoder pulse signal of the main servo motor in the underwear production equipment, the collected data of each sensor in the underwear production equipment, and the operating status of the underwear production equipment. The marking module 220 associates and marks the rotary encoder pulse signal with the collected data of each sensor, obtaining all sensor data marked with pulse sequence numbers. The alignment module 230 performs event sequence alignment on each sensor data according to all sensor data marked with pulse sequence numbers, obtaining all aligned sensor data. The confirmation module 240 determines the pulse signal deviation between the expected pulse signal and the rotary encoder pulse signal based on the operating status of the underwear production equipment. The calibration module 250 uses the pulse signal deviation to calibrate all aligned sensor data, obtaining all calibrated sensor data. The early warning module 260 matches all calibrated sensor data with preset causal association rules to determine each early warning component in the underwear production equipment and provides an early warning prompt for each early warning component. This system can achieve refined monitoring of the operating status of the underwear production equipment and accurate early warning of faults. The collaborative work of each module ensures an efficient and accurate processing flow from raw data to early warning information, thereby significantly improving the operational reliability and production efficiency of the equipment.

[0079] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the present invention specification.

Claims

1. An undergarment production equipment operating state data processing method, characterized by, The method comprises the following steps: acquiring the rotation encoder pulse signal of the main servo motor in the underwear production equipment, the collected data of each sensor in the underwear production equipment, and the running state of the underwear production equipment; associating and marking the rotation encoder pulse signal with the collected data of each sensor to obtain sensor data marked with pulse sequence numbers; aligning the event sequence of each sensor data according to the sensor data marked with pulse sequence numbers to obtain all aligned sensor data; determining the pulse signal deviation between the expected pulse signal and the rotation encoder pulse signal according to the running state of the underwear production equipment; calibrating all the aligned sensor data by using the pulse signal deviation to obtain calibrated all the sensor data; matching the calibrated all the sensor data with the preset causal correlation rule to determine each early warning component in the underwear production equipment and to give early warning prompts for each early warning component.

2. The method of claim 1, wherein The step of calibrating all the aligned sensor data by using the pulse signal deviation to obtain calibrated all the sensor data comprises the following steps: confirming all the deviation data of the aligned sensor data with signal deviation by using the pulse signal deviation; analyzing all the deviation data to obtain the deviation data type containing systematic drift or random noise; when the deviation data type is systematic drift, confirming the pulse sequence number offset, and calibrating the aligned sensor data to obtain calibrated all the sensor data; when the deviation data type is random noise, filtering the aligned sensor data to obtain calibrated all the sensor data.

3. The method of claim 2, wherein The step of analyzing all the deviation data to obtain the deviation data type containing systematic drift or random noise comprises the following steps: confirming the moving average value, trend slope, standard deviation, and instantaneous change rate of each deviation data in a continuous time period; judging the moving average value and trend slope of each deviation data in a continuous time period to confirm the random noise state in all the deviation data; judging the standard deviation and instantaneous change rate of each deviation data in a continuous time period to confirm the systematic drift state in all the deviation data; determining the superposition state of the random noise state and the systematic drift state under the same pulse sequence number; obtaining the deviation data type containing systematic drift or random noise according to the random noise state, the systematic drift state, and the superposition state.

4. The method of claim 1, wherein The step of determining the pulse signal deviation between the expected pulse signal and the rotation encoder pulse signal according to the running state of the underwear production equipment comprises the following steps: determining the component response time and the current working condition parameter of the underwear production equipment according to the running state of the underwear production equipment; determining the expected response time of the component according to the current working condition parameter and the historical recovery data; comparing the expected response time of the component with the component response time to obtain the instantaneous response deviation; determining the pulse signal deviation between the expected pulse signal and the rotation encoder pulse signal according to the instantaneous response deviation and the current working condition parameter.

5. The method of claim 4, wherein According to the underwear production equipment running state, the step of determining the component response time and the current working condition parameter of the underwear production equipment comprises: According to the underwear production equipment running state, the step of confirming the initial response time of each component and the initial parameter of each working condition of the underwear production equipment comprises: According to the initial response time of each component and the initial parameter of each working condition, the initial response time of each component and the current working condition parameter of the underwear production equipment are determined. According to the underwear production equipment running state, the step of confirming the initial response time of each component and the initial parameter of each working condition of the underwear production equipment comprises:

6. The method of claim 5, wherein According to the initial response time of each component and the initial parameter of each working condition, the initial response time of each component and the current working condition parameter of the underwear production equipment are determined. According to the initial response time of each component and the initial parameter of each working condition, the initial response time of each component and the current working condition parameter of the underwear production equipment are determined. The step of confirming the initial response time of each component and the initial parameter of each working condition of the underwear production equipment according to the underwear production equipment running state comprises: According to the initial response time of each component and the initial parameter of each working condition, the initial response time of each component and the current working condition parameter of the underwear production equipment are determined.

7. The method of claim 6, wherein The step of confirming the initial response time of each component and the initial parameter of each working condition of the underwear production equipment according to the underwear production equipment running state comprises: According to the initial response time of each component and the initial parameter of each working condition, the initial response time of each component and the current working condition parameter of the underwear production equipment are determined. The step of confirming the initial response time of each component and the initial parameter of each working condition of the underwear production equipment according to the underwear production equipment running state comprises: According to the initial response time of each component and the initial parameter of each working condition, the initial response time of each component and the current working condition parameter of the underwear production equipment are determined.

8. The method of claim 1, wherein The step of confirming the initial response time of each component and the initial parameter of each working condition of the underwear production equipment according to the underwear production equipment running state comprises: According to the initial response time of each component and the initial parameter of each working condition, the initial response time of each component and the current working condition parameter of the underwear production equipment are determined. The step of confirming the initial response time of each component and the initial parameter of each working condition of the underwear production equipment according to the underwear production equipment running state comprises:

9. The method of claim 1, wherein According to the initial response time of each component and the initial parameter of each working condition, the initial response time of each component and the current working condition parameter of the underwear production equipment are determined. The step of confirming the initial response time of each component and the initial parameter of each working condition of the underwear production equipment according to the underwear production equipment running state comprises: According to the initial response time of each component and the initial parameter of each working condition, the initial response time of each component and the current working condition parameter of the underwear production equipment are determined. The step of confirming the initial response time of each component and the initial parameter of each working condition of the underwear production equipment according to the underwear production equipment running state comprises:

10. A data processing system for the operating status of underwear production equipment, characterized in that, According to the initial response time of each component and the initial parameter of each working condition, the initial response time of each component and the current working condition parameter of the underwear production equipment are determined. The system comprises: An acquisition module is configured to acquire a rotary encoder pulse signal of a main servo motor in an underwear production equipment, acquisition data of each sensor in the underwear production equipment, and a running state of the underwear production equipment. A marking module is configured to associate and mark the rotary encoder pulse signal with the acquisition data of each sensor to obtain all sensor data marked with a pulse sequence number. The system comprises: An alignment module is configured to perform event sequence alignment on each of the sensor data according to all the sensor data marked with pulse numbers, to obtain all the aligned sensor data; A confirmation module is configured to determine a pulse signal deviation between an expected pulse signal and a rotary encoder pulse signal according to a running state of the underwear production equipment; A calibration module is configured to perform calibration processing on all the aligned sensor data by using the pulse signal deviation, to obtain calibrated all the sensor data; A warning module is configured to match the calibrated all the sensor data with a preset causal correlation rule, to determine each warning component in the underwear production equipment, and to perform a warning prompt on each warning component.

Images