A method and system for real-time monitoring of spunlace nonwoven fabric production process

By actively applying pressure disturbance and continuously collecting the motor current of the vacuum dehydration box, a highly sensitive anomaly detection in the spunlace nonwoven fabric production process was achieved, overcoming the shortcomings of traditional monitoring methods and improving the scientific rigor and consistency of the detection.

CN123067413APending Publication Date: 2026-11-10HANGZHOU HANFORD TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611578265.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-10-13
Publication Date
2026-11-10

AI Technical Summary

Technical Problem

In the existing spunlace nonwoven fabric production process, traditional monitoring methods lack sensitivity to progressive faults, cannot adapt to the differences in current response characteristics of the vacuum dehydration box at different machine speeds, and cannot identify early physical faults such as dehydration box filter damage or spunlace machine nozzle blockage.

Method used

By actively applying pressure disturbances of known amplitude and duration to the hydroentanglement machine, the current of the vacuum dehydration tank motor is synchronously and continuously collected and normalized. The current recovery time is automatically determined using a preset proportional threshold, and anomaly detection is performed by combining the standard recovery time of the current operating speed.

Benefits of technology

It achieves highly sensitive and proactive detection of the production process, enabling early detection of initial anomalies that are difficult to identify with traditional monitoring methods, without the need for additional hardware sensors, thus improving the scientific rigor and consistency of the detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123067413A_ABST
    Figure CN123067413A_ABST
Patent Text Reader

Abstract

This application discloses a real-time monitoring method and system for the production process of spunlace nonwoven fabric, belonging to the field of monitoring technology. It includes: acquiring the current operating speed of the production line; determining the amplitude, duration, and standard recovery time of a pressure disturbance based on preset data; generating a control signal to drive the spunlace machine to cause a disturbance of a specified amplitude and duration in the spunlace pressure; continuously collecting the motor current value of the vacuum dehydration tank; normalizing all current values ​​using the average current before the disturbance as a reference value; comparing the normalized current values ​​with a preset proportional threshold in chronological order after the disturbance ends to determine the recovery time and calculate the recovery time; and determining that an abnormality has occurred in the production process when the recovery time is less than the standard recovery time. This invention, through actively applying pressure disturbances and normalizing the dynamic analysis of the current response in the dehydration tank, can sensitively detect abnormalities, unaffected by changes in operating speed, thus improving the accuracy and timeliness of production monitoring.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of monitoring technology, and in particular to a method and system for real-time monitoring of the spunlace nonwoven fabric production process. Background Technology

[0002] Spunlace nonwoven fabric is produced by using high-pressure water jets to propel a fiber web, causing the fibers to entangle and form a fabric. On a spunlace production line, the spunlace machine and vacuum dewatering chamber are key pieces of equipment. The spunlace pressure directly affects the fiber entanglement effect, while the motor current of the vacuum dewatering chamber reflects the dewatering load and system operating status. Real-time monitoring of the production process and timely detection of anomalies are crucial for ensuring product quality and equipment safety.

[0003] Currently, monitoring during production mainly relies on on-site inspections by operators and setting fixed upper and lower limit alarm thresholds for individual process parameters. However, this traditional monitoring method has significant shortcomings: firstly, it is passive monitoring, only triggering alarms when parameters significantly deviate from the set range, lacking sensitivity to gradual faults in their early stages; secondly, it does not consider the impact of production line operating speed on the system's dynamic characteristics. The response characteristics of the vacuum dehydration tank current vary greatly at different speeds, and fixed thresholds cannot adapt to changes in operating conditions, easily leading to missed or false alarms. Furthermore, some physical faults, such as damaged dehydration tank filters or severe blockage of hydroentanglement machine nozzles, may initially manifest as an abnormally rapid system recovery speed rather than simply exceeding limits, and traditional threshold alarms cannot effectively identify such anomalies. Summary of the Invention

[0004] This application provides a method and system for real-time monitoring of the spunlace nonwoven fabric production process to improve the above-mentioned problems.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] Firstly, this application proposes a real-time monitoring method for the production process of spunlace nonwoven fabric, applied to a real-time monitoring system for the production process of spunlace nonwoven fabric. The system includes a monitoring terminal and a spunlace nonwoven fabric production line, which includes a vacuum dewatering chamber and a spunlace machine. The method is executed by the monitoring terminal and includes: acquiring the current operating speed of the spunlace nonwoven fabric production line; determining the pressure disturbance amplitude, duration of action, and standard recovery time from preset data based on the current operating speed; generating a control signal based on the pressure disturbance amplitude and duration of action, wherein the control signal is configured to drive the spunlace machine to make the spunlace pressure change amplitude reach the pressure disturbance amplitude and continue to act for the specified duration; initiating continuous acquisition of the motor current value of the vacuum dewatering chamber; determining the time of outputting the control signal as the output time, and... The end time is determined based on the duration of action, and the control signal is output to the hydroentangling machine. During continuous data acquisition, time and current data points with acquisition times earlier than the output time are identified, and the arithmetic mean of multiple current values ​​among these data points is used as the reference current value. All current values ​​acquired in multiple continuous acquisitions are divided by the reference current value to obtain multiple normalized current values. All time and current data points with acquisition times later than the end time are acquired, arranged in chronological order, and their corresponding normalized current values ​​are compared sequentially with a preset proportional threshold. The acquisition time at which the first acquisition time falls below the preset proportional threshold is taken as the recovery time. The difference between the recovery time and the end time is determined as the recovery time. If the recovery time is less than the standard recovery time, an anomaly is determined in the production process.

[0007] Therefore, by actively applying pressure disturbances of known amplitude and duration to the hydroentangling machine, simultaneously and continuously collecting and normalizing the motor current of the vacuum dehydration tank, and using the steady-state current before the disturbance as a benchmark to eliminate differences in operating conditions, the current recovery time is automatically determined using a preset proportional threshold. Finally, the actual recovery time is compared with the standard recovery time based on the current operating speed, thus achieving real-time active detection of anomalies in the production process. This method is unaffected by fluctuations in operating speed, has high detection sensitivity, can detect early anomalies that are difficult to identify using traditional passive monitoring, and requires no additional hardware sensors, making it highly applicable in engineering projects.

[0008] In conjunction with the first aspect, optionally, based on the current operating speed, the pressure disturbance amplitude, duration, and standard recovery time corresponding to the current operating speed are determined from preset data. The preset data is determined by the following steps: acquiring historical pressure and current values ​​of the spunlace nonwoven fabric production line operating at multiple different speeds; determining multiple pressure fluctuation events based on the historical pressure values, wherein a pressure fluctuation event is an event where the historical pressure value deviates from a steady state and recovers to a steady state, and the deviation of the historical pressure value exceeds a preset amplitude threshold; and normalizing the historical current values ​​collected during the pressure fluctuation event based on the historical current values ​​at the steady state before the fluctuation, to obtain each pressure wave... The normalized historical current value corresponding to the dynamic event is used; the moment of recovery to steady state is taken as the target recovery start time, and the time from the target recovery start time to the normalized historical current value reaching the preset recovery threshold is obtained and determined as the target recovery time; the standard recovery time at the operating speed is determined based on the minimum value among all target recovery times corresponding to the operating speed; the pressure disturbance amplitude corresponding to the operating speed is determined based on the sum of the maximum deviation amplitude and the first preset additional value among all pressure fluctuation events corresponding to the operating speed; the duration of action corresponding to the operating speed is determined based on the sum of the maximum duration of pressure deviation and the second preset additional value among all pressure fluctuation events corresponding to the operating speed.

[0009] Therefore, by collecting historical pressure and current data at multiple operating speeds, automatically extracting pressure fluctuation events and normalizing them, and using the minimum recovery time as the standard recovery time, the system's limit recovery capability under fault-free conditions can be accurately captured. The maximum deviation amplitude and the longest deviation duration are respectively added with corresponding margins as active disturbance parameters, ensuring that the test stimulus fully excites the system response while avoiding excessive disturbances that could adversely affect equipment and products. This method is entirely based on objective statistical analysis of actual operating data, eliminating the need for manual parameter setting. This ensures that the diagnostic benchmark closely matches the characteristics of the production line, improving the scientific rigor and consistency of monitoring.

[0010] In conjunction with the first aspect, optionally, after determining that an abnormality has occurred in the production process, the method further includes: obtaining the minimum value among all normalized current values ​​obtained between the end time and the recovery time, and determining it as the minimum current value; comparing the minimum current value with a preset minimum current threshold; if the minimum current value is lower than the preset minimum current threshold, then confirming that a first type of abnormality has occurred, otherwise confirming it as a second type of abnormality.

[0011] Therefore, after identifying an anomaly, by further investigating the minimum drop depth during the current recovery process after the disturbance ends and comparing it with a preset minimum current threshold, the general anomaly can be refined into Type I and Type II anomalies. This classification gives the diagnostic results a clearer physical meaning, helping to distinguish whether the anomaly is caused by a sudden change in the hardware physical state or by a deviation in the process parameter settings.

[0012] In conjunction with the first aspect, optionally, the preset minimum current threshold is obtained from preset data based on the current operating speed, wherein the preset data further includes: the historical minimum value of the normalized current value in historical normal pressure fluctuation events when running at different operating speeds, and the preset minimum current threshold is determined based on the historical minimum value.

[0013] Therefore, the preset minimum current threshold is related to the operating speed and is derived based on the statistical analysis of the normalized maximum current drop depth observed in historical normal events. This ensures that the current drop threshold can automatically adapt to the normal response characteristics under different production speeds. This speed self-matching mechanism effectively eliminates misjudgments caused by the natural variation in current drop amplitude due to speed changes, further improving the accuracy of anomaly classification.

[0014] In conjunction with the first aspect, the method may optionally further include: when a first type of abnormality is confirmed, generating a first maintenance indication signal to prompt for inspection of the filter screen of the vacuum dehydration tank and the nozzle of the hydroentangling machine; and when a second type of abnormality is confirmed, generating a second maintenance indication signal to prompt for the hydroentangling pressure setting value.

[0015] Therefore, based on the anomaly classification results, differentiated maintenance instruction signals are automatically generated, directly prompting operators to check the vacuum dehydration box filter and the hydroentangling machine nozzle, or to verify the hydroentangling pressure setting, thus translating the diagnostic results into specific, actionable maintenance actions. This closed-loop instruction mechanism significantly shortens fault location and troubleshooting time, reduces unnecessary disassembly and downtime, and improves the overall maintenance efficiency and intelligence level of the production line.

[0016] In conjunction with the first aspect, the method may optionally further include: obtaining the cumulative operating parameters of the spunlace nonwoven fabric production line; correcting the standard recovery time based on the cumulative operating parameters to obtain the dynamic standard recovery time; and determining that an abnormality has occurred in the production process if the recovery time is less than the standard recovery time, including: determining that an abnormality has occurred in the production process if the recovery time is less than the dynamic standard recovery time.

[0017] Therefore, by acquiring the cumulative operating parameters of the production line and dynamically correcting the standard recovery time, the benchmark for anomaly detection can be automatically adjusted to follow the normal aging or break-in process of the equipment, avoiding the misjudgment of reasonable performance drift caused by long-term equipment operation as process anomalies. This adaptive threshold strategy significantly reduces the false alarm rate in long-term use, ensuring the effectiveness and stability of the monitoring solution throughout the entire equipment lifecycle.

[0018] In conjunction with the first aspect, optionally, the cumulative operating parameters include cumulative operating time or cumulative output, and the standard recovery time is corrected by: querying a preset degradation mapping relationship based on the cumulative operating parameters to obtain a degradation coefficient, wherein the degradation coefficient is a positive number less than or equal to 1; multiplying the standard recovery time by the degradation coefficient to obtain the dynamic standard recovery time.

[0019] Therefore, by using cumulative operating time or output as an objective indicator to measure the degree of equipment use, and converting it into a degradation coefficient no greater than 1 through a preset degradation mapping relationship, and then restoring the time consumption using a multiplicative correction standard, a quantitative and calibrable dynamic threshold adjustment mechanism is achieved. This method is simple to calculate, easy to implement, and can adapt to the actual aging patterns of various types of equipment according to different degradation mappings, thus enhancing the flexibility and accuracy of degradation compensation.

[0020] In conjunction with the first aspect, optionally, the degradation mapping relationship is determined by fitting historical recovery time data of the spunlace nonwoven fabric production line under different cumulative operating parameters and when no abnormalities occur in the production process, wherein the degradation coefficient decreases monotonically with the increase of cumulative operating parameters.

[0021] Therefore, the degradation mapping relationship is directly derived from the historical recovery time data of the production line under known normal conditions. By fitting and establishing a monotonic relationship between cumulative operating parameters and degradation coefficients, the degradation model has an objective data basis and a clear physical trend. This data-driven approach can truly reflect the individualized degradation trajectory of the equipment, ensuring that the dynamic standard recovery time always matches the actual health status of the equipment, further improving the accuracy of anomaly detection and early fault warning capabilities.

[0022] Secondly, this application proposes a real-time monitoring system for the production process of spunlace nonwoven fabric, including a monitoring terminal and a spunlace nonwoven fabric production line. The spunlace nonwoven fabric production line includes a vacuum dewatering chamber and a spunlace machine. The system also includes:

[0023] The first acquisition module is used to acquire the current operating speed of the spunlace nonwoven fabric production line;

[0024] The first determining module is used to determine the pressure disturbance amplitude, duration of action, and standard recovery time from preset data based on the current operating speed.

[0025] The generation module is used to generate a control signal based on the pressure disturbance amplitude and the duration of action. The control signal is configured to drive the hydroentanglement machine to make the hydroentanglement pressure change amplitude reach the pressure disturbance amplitude and the duration of action.

[0026] The data acquisition module is used to continuously acquire the current value of the motor in the vacuum dehydration box.

[0027] The second determining module is used to determine the time of output control signal as output time, and determine the end time based on the duration of action, and output control signal to hydroentanglement machine;

[0028] The third determination module is used to determine the time and current data points whose acquisition time is earlier than the output time in the time and current data points during the continuous acquisition process, and to determine the arithmetic mean of multiple current values ​​in the time and current data points as the reference current value.

[0029] The fourth determination module is used to divide all current values ​​from multiple continuous acquisitions by the reference current value to obtain multiple normalized current values.

[0030] The second acquisition module is used to acquire all time and current data points whose acquisition time is later than the end time, arrange them in chronological order, and compare the corresponding normalized current values ​​with the preset ratio threshold in turn, and take the acquisition time when the first acquisition time is lower than the preset ratio threshold as the recovery time.

[0031] The fifth determining module is used to determine the recovery time as the difference between the recovery time and the end time.

[0032] The sixth determination module is used to determine that an anomaly has occurred in the production process if the recovery time is less than the standard recovery time.

[0033] A third aspect of the present invention provides a processing apparatus, the processing apparatus comprising:

[0034] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method proposed in the first aspect of the present invention.

[0035] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in the first aspect of the present invention. Attached Figure Description

[0036] Figure 1This is a flowchart illustrating a real-time monitoring method for the production process of spunlace nonwoven fabric proposed in an embodiment of this application.

[0037] Figure 2 This is a schematic diagram of the structure of a real-time monitoring system for the production process of spunlace nonwoven fabric proposed in an embodiment of this application.

[0038] Figure 3 This is a schematic diagram of the structure of a processing device proposed in an embodiment of this application. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] This embodiment provides a real-time monitoring method for the production process of spunlace nonwoven fabric, which is executed by a monitoring terminal, such as an industrial control computer, embedded processor or cloud server, or may also be executed by an edge computing gateway or distributed control node, and is applied to a spunlace nonwoven fabric production line including a vacuum dehydration box and a spunlace machine.

[0041] like Figure 1 As shown, the method includes steps S101 to S110.

[0042] S101: Obtain the current operating speed of the spunlace nonwoven fabric production line.

[0043] Specifically, the current production line speed can be read in real time from the main control equipment (such as a PLC or motion controller). This speed value represents the real-time cycle time of the fiber web conveying and hydroentangling processes. For example, the production line speed range is typically 10–200 m / min, and can be read via industrial protocols such as ModbusTCP, PROFIBUS, or EtherCAT; alternatively, a separate speed sensor, such as an encoder, can be used to directly measure the roller rotation speed and calculate the linear speed by combining it with the roller diameter.

[0044] S102: Based on the current operating speed, determine the pressure disturbance amplitude, duration of action, and standard recovery time from preset data.

[0045] Understandably, in this application, the current operating speed is used as the retrieval basis. A set of pre-calibrated and stored tables showing the relationship between operating speed and process parameters is searched or interpolated to determine three key values ​​corresponding to that speed, including:

[0046] Pressure disturbance amplitude: that is, the magnitude of the change that the hydroentanglement pressure needs to be actively changed;

[0047] Duration of action: that is, the length of time the pressure change needs to be maintained;

[0048] Standard recovery time: that is, under normal, abnormal operating conditions, the reference time required for the system to recover to a stable state from the end of pressure disturbance.

[0049] Understandably, the preset data typically comes from historical experiments or large-scale production data analysis, encapsulating normal dynamic characteristics at different speeds. The relational table can be stored in the monitoring terminal's local flash memory or deployed in a remote historical database, retrieved via query statements. Interpolation methods, such as linear interpolation or spline interpolation, can smoothly obtain the corresponding parameter values ​​when the current operating speed falls between two preset speed nodes. Alternatively, instead of relying on table lookups, a pre-trained regression model, such as multinomial regression or neural networks, can be directly invoked based on the current operating speed to calculate the three key values ​​in real time.

[0050] Specifically, in this application, the preset data can be determined by the following steps S201~S207:

[0051] S201: Obtain historical pressure and current values ​​of the spunlace nonwoven fabric production line when it is running at multiple different operating speeds.

[0052] During the commissioning, trial run, or long-term normal production phases of the production line, a data acquisition system can simultaneously record two time-series data points under typical operating conditions such as 50m / min, 80m / min, and 120m / min. One data point records the actual hydroentangling pressure of the hydroentangling machine, and the other records the actual current of the vacuum dehydration tank motor. Both parameters are continuously recorded at the same high sampling frequency, covering a large time period from steady-state operation to various minute fluctuations. The purpose of acquiring this historical data is understandably to extract the dynamic response characteristics of the system from the actual production process, providing factual evidence for proactive disturbance diagnosis. These speed values ​​cover the normal operating range of the production line, ensuring that the subsequently established preset data has sufficient representativeness of operating conditions. Additionally, simulated historical data can be generated using a digital twin model of the production line as a supplement, especially when it is difficult to collect sufficient realistic fluctuation events at certain speed ranges.

[0053] S202: Based on historical pressure values, identify multiple pressure fluctuation events, where a pressure fluctuation event is an event in which the historical pressure value deviates from the steady state and recovers to the steady state, and the deviation of the historical pressure value exceeds a preset amplitude threshold.

[0054] Specifically, historical pressure time series at each operating speed can be analyzed to identify pressure fluctuation events that meet specific conditions.

[0055] Understandably, pressure data must exhibit a clear "steady-state ~ deviation ~ recovery" process. Before an event occurs, the pressure value needs to remain relatively stable for a period of time; for example, fluctuations within 5 consecutive seconds not exceeding ±2% can be considered steady-state. Then, the pressure value experiences a significant deviation exceeding a preset threshold; finally, the pressure value gradually returns and stabilizes again within the original steady-state range. The steady-state determination condition can also be replaced with: fluctuations within 3 consecutive seconds not exceeding ±1%, or the standard deviation based on a sliding window being lower than a preset threshold. The preset threshold can be set, for example, to 3 bar or 5 bar, determined according to the normal pressure fluctuation level of the production line.

[0056] It should be noted that only events with sufficiently large deviations are included, because small fluctuations may simply be noise and cannot elicit an observable system response. Through this screening, several natural disturbance events with analytical value can be extracted from massive historical data, each recording a complete system dynamic process caused by pressure fluctuations.

[0057] S203: Based on the historical current value at steady state before the fluctuation, normalize the historical current value collected during the pressure fluctuation event to obtain the normalized historical current value corresponding to each pressure fluctuation event.

[0058] Understandably, in each pressure fluctuation event, current data can be obtained throughout the entire process of the event, including a current record before the pressure deviation begins, during the deviation, and after the recovery is completed.

[0059] To eliminate the differences in absolute current levels caused by different operating speeds, production batches, or equipment conditions, it is necessary to normalize the current using the steady-state current before the event disturbance as a benchmark. Specifically, all current samples during the steady-state period before the pressure fluctuation can be taken, and their arithmetic mean can be calculated as the reference current for the event. Then, the current value at each moment throughout the entire event is divided by this reference current to obtain a dimensionless normalized current value. Understandably, after this processing, the normalized current value at steady state is close to 1, while the current change caused by the pressure disturbance will show a curve deviating from 1. Normalization makes the current responses under different events and speeds comparable. When calculating the reference current, the median or a truncated average after removing outliers can also be used, for example, averaging after removing the highest and lowest 5% of data, to reduce the impact of individual spikes.

[0060] S204: Take the moment when the current recovers to a steady state as the target recovery start time, and obtain the time when the normalized historical current value reaches the preset recovery threshold from the target recovery start time, and determine it as the target recovery time.

[0061] Understandably, in each pressure fluctuation event, it is necessary to quantify how quickly the current response recovers from the disturbance to steady state. To this end, a clear recovery timing starting point is first determined, i.e., the moment when the pressure value returns to steady state is selected as the target recovery start moment. From this moment, the trajectory of the normalized current value is observed.

[0062] After the pressure returns to steady state, due to the presence of fluid and mechanical inertia, the current in the dehydration tank will not immediately return to the level before the disturbance, but will undergo a transition process to gradually approach 1. A preset recovery threshold, such as 0.98, is set, indicating that the current has recovered to 98% of the reference value. The time elapsed from the start of recovery to the moment when the normalized current value first reaches this threshold is recorded; this is called the target recovery time corresponding to the event. This time characterizes the time required for the vacuum dehydration tank motor current to complete its response and essentially return to normal levels under naturally occurring pressure fluctuations. The preset recovery threshold can also be set to 0.95, 0.97, or 1.02, etc., adjusted according to accuracy requirements; for systems with overshoot during the recovery process, the threshold can be set to a value greater than 1, such as 1.03.

[0063] S205: Determine the standard recovery time at the operating speed based on the minimum of all target recovery times corresponding to the operating speed.

[0064] Understandably, for the same operating speed, multiple target recovery times can be calculated from various historical pressure fluctuation events at that speed. These recovery times are discretely distributed due to the subtle differences in each fluctuation. Here, the minimum value is taken as the standard recovery time at that operating speed. The minimum value represents the fastest current recovery capability that the system can exhibit under normal conditions such as no faults or blockages at that speed. This fastest speed is determined by the physical characteristics of the production line itself, such as pipeline resistance, vacuum chamber volume, and motor response, and is a relatively fixed limit value. Based on this minimum recovery time, in subsequent active monitoring, if the measured recovery time is shorter than this limit value, it means that the physical characteristics of the system have changed, such as an unexpected decrease in dehydration resistance, thus allowing the detection of potential anomalies. For example, if five target recovery times are obtained at a certain speed {2.3s, 2.1s, 2.5s, 1.9s, 2.2s}, then the standard recovery time is taken as 1.9s. Alternatively, instead of directly taking the minimum value, one can take the 5th percentile of the recovery time of all targets, or take the minimum value multiplied by a safety factor of 0.9, in order to reduce the impact of individual extremely short-duration events.

[0065] S206: Based on the sum of the maximum deviation amplitude and the first preset additional value among all pressure fluctuation events corresponding to the operating speed, determine the pressure disturbance amplitude corresponding to the operating speed.

[0066] To implement proactive diagnostics, a hydroentanglement pressure disturbance with a defined amplitude needs to be artificially generated. This disturbance amplitude cannot be too small, otherwise it won't elicit a noticeable response; nor can it be too large, otherwise it will interfere with normal production or even damage the equipment. Therefore, from all historical pressure fluctuation events at this operating speed, the maximum value of the pressure deviation amplitude is extracted—that is, the largest absolute difference between the pressure from the steady-state value and the point of maximum deviation in each event. This maximum value represents the largest pressure fluctuation that has occurred during natural production, indicating the range that the system can withstand and stably recover from. Then, based on this maximum value, a first preset additional value is added as a safety margin, ensuring that the proactive disturbance has sufficient strength to significantly stimulate dynamic changes in the dehydration tank current, while not exceeding the equipment's safe operating range. The resulting value is the pressure disturbance amplitude corresponding to that operating speed. The first preset additional value can be set segment by segment according to speed, for example, 1 bar for low speed, 2 bar for medium speed, and 3 bar for high speed; or it can be a fixed percentage of the maximum pressure deviation amplitude, such as 20%, as the additional value.

[0067] S207: Based on the sum of the maximum duration of pressure deviation and the second preset additional value among all pressure fluctuation events corresponding to the operating speed, determine the duration of action corresponding to the operating speed.

[0068] Similarly, the duration of the active disturbance also needs to be reasonably determined. If the duration is too short, the system may not have enough time to complete a sufficient dynamic response; if the duration is too long, it may affect product quality or cause unnecessary production disturbances. From all pressure fluctuation events at this operating speed, extract the duration of pressure deviation for each event and find the maximum value.

[0069] The maximum value reflects the longest possible duration of pressure deviation under natural fluctuations. Based on this, a second preset additional value is added to ensure that the actively applied pressure disturbance lasts long enough to guarantee that the current in the dehydration tank undergoes a complete transition process, thus making the subsequently measured recovery time more reliable. This determined duration is based on the most severe historical data while allowing for an appropriate margin, balancing the effectiveness and safety of the test. The typical value for the second preset additional value is 0.3–1.0 seconds, but it can also be set proportionally to the duration of the maximum deviation, such as 30% of the duration.

[0070] S103: Generate a control signal based on the pressure disturbance amplitude and duration of action, wherein the control signal is configured to drive the hydroentangling machine to make the hydroentangling pressure change amplitude reach the pressure disturbance amplitude and continue to act for the duration specified in the original text.

[0071] Understandably, based on the two parameters determined in S102, an active excitation signal is generated, for example, a step signal superimposed on the existing spunlace pressure setpoint. For instance, the pressure regulating device of the spunlace machine, such as a variable frequency pump speed setting or a proportional valve opening command, can be instructed to generate a pressure change, the magnitude of which is exactly equal to the pressure disturbance amplitude, and the duration of this change is exactly equal to the duration of action. It should be noted that this step generates a command that has not yet been output. The excitation signal is not limited to a step form; it can also be a trapezoidal wave or a half-sine wave, as long as it can excite the system dynamics on the rising and falling edges of the disturbance. The control signal can be output to the spunlace machine drive unit via 4-20mA analog or digital communication (such as EtherCAT).

[0072] S104: Start continuous acquisition of the motor current value of the vacuum dehydration box.

[0073] Understandably, a high-speed acquisition process of the vacuum dehydration chamber motor current is triggered before the control signal is output to the hydroentangling machine. The acquired data is a sequence of current values ​​with precise timestamps, i.e., time and current data points. The vacuum dehydration chamber motor current directly reflects the dehydration resistance and vacuum level, and is closely related to the changes in the fiber web structure caused by hydroentangling disturbance. This acquisition will cover the complete time period before, during, and after the disturbance. The acquisition frequency can be set to, for example, 20Hz or 50Hz, and can be adjusted according to the rate of change of the motor current, generally between 10 and 100Hz; the acquisition device can use a current transformer in conjunction with a high-speed data acquisition card, or directly read the current feedback signal output by the frequency converter.

[0074] S105: Determine the time when the control signal is output as the output time, and determine the end time based on the duration of action, and output the control signal to the hydroentangling machine.

[0075] Specifically, the output time can be defined as That is, the instant when the control signal is actually sent to the actuator of the hydroentangling machine, and at the same time, the time when the disturbance ends is calculated based on the duration Δt. = +Δt, in At that moment, the monitoring terminal completed the physical output of the control signal, and the water jet pressure began to change.

[0076] S106: In the continuous acquisition process, determine the time and current data points whose acquisition time is earlier than the output time, and determine the arithmetic mean of multiple current values ​​in the time and current data points as the reference current value.

[0077] Specifically, from the continuously acquired sequence, the output time... As a boundary, filter out all timestamps earlier than The data points are the points where data was collected before the pressure disturbance was applied. The arithmetic mean of the current values ​​contained at these points is denoted as . .

[0078] Understandably, the mean value represents the steady-state load current level of the vacuum dehydration tank motor under no active disturbance, essentially reflecting the normal operating point under the current conditions. To improve the robustness of the reference value, outliers (such as those exceeding ±3σ) can be removed from these current values ​​before calculating the average, or the median can be used as the reference current value.

[0079] S107: Divide all current values ​​from multiple continuous acquisitions by the reference current value to obtain multiple normalized current values.

[0080] Understandably, for each raw current data I(t) acquired during and after S104 to S105, it is divided by the reference current value S. The dimensionless normalized current value is obtained. (t)=I(t) / .

[0081] After normalization, the steady-state value is close to 1, and deviations caused by disturbances manifest as increases or decreases relative to 1. This processing eliminates differences in the absolute value of the current caused by different operating speeds or load fluctuations, making the dynamic response shapes under different operating conditions comparable and improving the universality of comparison. For example, if the reference current... =50A, and the current sampled at a certain moment is 40A, then the normalized current value is 0.8.

[0082] S108: Acquire all time and current data points whose acquisition time is later than the end time, arrange them in chronological order, and compare the corresponding normalized current values ​​with the preset ratio thresholds in turn. Use the acquisition time when the first acquisition time is lower than the preset ratio threshold as the recovery time.

[0083] Specifically, in all the data continuously collected by S104, the timestamp was taken later than the end time. This refers to the portion of the time when the disturbance terminates. Arranging these data points in ascending order of timestamps yields a sequence.

[0084] Then, the normalized current value corresponding to each data point is extracted one by one from front to back. This is then compared to a pre-set threshold ratio, such as 0.95, whose value can be set based on engineering experience. Once a data point is found... When the value first falls below the threshold, the normalized current is considered to have recovered and fallen below the threshold, and the corresponding acquisition timestamp is marked as recovery time t2. If the disturbance ends but the normalized current never falls below the threshold again, a timeout judgment can be triggered. The completion point of dynamic current recovery is captured by threshold comparison. The proportional threshold can be replaced with a dynamic threshold calculated based on historical normal recovery data, such as the 3σ boundary of the lower limit of normalized current fluctuation during normal recovery; or a judgment method based on the rate of change of the curve slope can be used, which does not depend on a fixed threshold.

[0085] S109: The difference between the recovery time and the end time is determined as the recovery time.

[0086] Recovery time obtained using S108 Subtract the end time To obtain the time difference = - This refers to the recovery time. This time reflects the duration from the removal of the pressure disturbance to the recovery of the vacuum dehydration tank motor current response to near-normal levels, indicated by a normalized value below a preset proportional threshold.

[0087] S110: If the recovery time is less than the standard recovery time, then an anomaly has occurred in the production process.

[0088] Specifically, the actual recovery time Compared with the standard recovery time found in the preset data Compare. If < If the standard recovery time is abnormally short, it indicates a problem in the current production process. Understandably, the standard recovery time is the fastest recovery time under fault-free conditions, calculated from a large amount of historical data, and is equivalent to the normal limit of the system's physical characteristics. When the actual recovery time is abnormally short of this limit, it indicates a sudden change in the system's resistance, damping, or fluid flow path. For example, a damaged filter in the vacuum dehydration tank could cause excessively rapid dehydration, or a clogged nozzle in the hydroentangling machine could cause changes in reflected pressure. These are often precursors to component failure or process degradation, thus triggering an abnormal alarm.

[0089] To further differentiate the anomaly type by utilizing the drop depth of the current response curve after the disturbance ends, optionally, as an implementation method, after determining that an anomaly has occurred in the production process, the following steps may also be included:

[0090] S111: Obtain the minimum value among all normalized current values ​​obtained between the end time and the recovery time, and determine it as the minimum current value.

[0091] exist arrive During this period, the motor current of the vacuum dehydration tank underwent a complete transition from a disturbed state to a steady-state recovery. Continuous data acquisition has recorded all timestamped current data points within this period, and these current values ​​have all been converted to normalized current values. In this step, we can extract all data points that satisfy the time stamp from the acquired data. ≤t≤ The normalized current values ​​are compared to find the minimum value, which is defined as the minimum current value. This minimum value reflects the maximum deviation depth reached by the current in the dehydration tank during the process of returning to normal level after the active stress is eliminated. In other words, the lower the value, the more severe the instantaneous drop in current and the greater the downward amplitude of the system response.

[0092] S112: Compare the minimum current value with the preset minimum current threshold.

[0093] Understandably, the minimum current value is a dynamic characteristic extracted from the actual response. To give this characteristic diagnostic significance, a pre-defined reference standard, namely a preset minimum current threshold, can be introduced. This threshold is a constant with the same dimensions as the normalized current, such as 0.7 or 0.8, representing the lowest limit that the current is allowed to reach during recovery within a normal or acceptable range of abnormal fluctuations. The task of this step is to perform a numerical comparison, that is, to directly compare the actual minimum current value with the preset minimum current threshold to determine whether the former is lower than the latter.

[0094] Furthermore, the preset minimum current threshold is obtained from preset data based on the current operating speed, wherein the preset data also includes:

[0095] When running at different operating speeds, the lowest normalized current value in historical normal pressure fluctuation events is used as the basis for determining the preset minimum current threshold.

[0096] Specifically, during previous commissioning, trial operation, or long-term normal production, the production line has accumulated a large amount of historical pressure and current data at various operating speeds. This step focuses on pressure fluctuation events that have been confirmed as normal. "Normal" means that when the event occurs, all equipment on the production line is in a healthy state—no faults, no damage, no blockages—the process parameters are set according to standards, and the product quality has passed inspection. Only events that meet these conditions can have their current response characteristics used as a normal benchmark.

[0097] For each operating speed, all records identified as pressure fluctuation events are extracted from historical data that meet the above normal conditions. Each event contains a complete current response curve, which has been converted into a dimensionless sequence of normalized current values ​​using a normalization method. In this sequence, due to the influence of pressure deviation and recovery processes, the normalized current value will not always remain around 1, but will fluctuate downwards. In this step, the lowest value of the normalized current that has ever appeared over the entire time span of the event can be found and recorded as the historical lowest value of the normalized current for that normal pressure fluctuation event.

[0098] Taking a certain operating speed as an example, several normal pressure fluctuation events may be recorded at that speed. For each event, a historical minimum value can be extracted. For example, the minimum value for the first event is 0.80, the second is 0.77, the third is 0.82, and the fourth is 0.79. The differences in these values ​​may stem from subtle differences in each fluctuation, minor fluctuations in the uniformity of the fiber web upstream of the production line, or measurement noise, but they collectively depict the normal drop depth range exhibited by the system in a healthy state at that speed.

[0099] Repeat the above operation for each preset running speed to eventually form a table corresponding to the running speed and the normal historical minimum value sample set.

[0100] After collecting several historical minimum value samples at a certain operating speed, a single value needs to be extracted from them using statistical methods as the preset minimum current threshold at that speed. This threshold will serve as a reference boundary between normal and abnormal conditions: when the minimum current value obtained from real-time monitoring is lower than this boundary, it means that the actual drop depth has exceeded the limits of all historical normal performance.

[0101] For example, the minimum value in the sample can be directly taken, that is, the minimum value among all historical minimum values ​​can be directly used as the preset minimum current threshold. This approach is the most stringent, meaning that as long as the minimum current value measured in real time is lower than the minimum value of any normal event in history, it is considered an abnormal drop.

[0102] Alternatively, a lower bound can be used, which involves calculating the mean μ and standard deviation σ of the sample set, and then taking μ–N×σ (N is typically 2 or 3) as the threshold. This method eliminates isolated low values ​​caused by extreme noise or brief transients in individual samples, making the threshold more statistically significant, while still ensuring that the minimum value of the vast majority of normal events is above the threshold. Alternatively, the first percentile of all historical minimum values ​​can be used, or the minimum value multiplied by a safety margin of 0.9 can be taken as the final threshold.

[0103] Regardless of the method used, an independent preset minimum current threshold is ultimately determined for each operating speed and stored in a preset data table, associated with the corresponding operating speed. During the real-time monitoring phase, the appropriate threshold can be directly retrieved from this table based on the current operating speed, and used for subsequent comparison and judgment of the minimum current value.

[0104] By employing the statistical determination method based on historical normal data, the preset minimum current threshold completely eliminates the problem of arbitrary setting by human experience. It is rooted in the actual dynamic performance of the production line under fault-free conditions and adapts automatically to changes in operating speed, thereby improving the accuracy of abnormal drop depth judgment.

[0105] S113: If the minimum current value is lower than the preset minimum current threshold, then the first type of abnormality is confirmed; otherwise, it is confirmed as the second type of abnormality.

[0106] Furthermore, if the minimum current value is lower than the preset minimum current threshold, it indicates that after the pressure disturbance is removed, the motor current in the dehydration tank not only recovers faster than the normal maximum speed, but also drops to an abnormally low level during this process. This combination of rapid recovery and deep drop usually points to a sudden change in certain components in the system circuit, such as a sudden drop in dehydration resistance due to a damaged filter screen in the vacuum dehydration tank, or a change in the water needle reflection pressure due to severe blockage of the nozzle in the hydroentangler machine. These factors can drastically change the fluid load, resulting in an abnormally deep current trough. Therefore, this type of situation is identified as a Type I anomaly.

[0107] Optionally, when a Type I anomaly is confirmed, a first maintenance indication signal is generated to prompt inspection of the filter screen of the vacuum dehydration chamber and the nozzles of the hydroentangling machine. Understandably, the recovery process of the dehydration chamber motor current after an active pressure disturbance is applied and then removed reflects the dynamic changes in the dehydration load. If the filter screen of the vacuum dehydration chamber is damaged or perforated, its dehydration resistance will suddenly decrease, resulting in faster vacuum establishment and smoother airflow. The motor current will drop rapidly after the pressure is removed, falling to a lower trough than normal due to the lighter load. Similarly, if the nozzles of the hydroentangling machine become partially clogged or worn, the distribution, impact force, and reflection pressure of the high-pressure water jets will change, affecting not only the fiber web entanglement effect but also the moisture distribution and vacuum load at the dehydration chamber inlet. Both of these situations represent sudden physical variations, rather than gradual process drift.

[0108] Therefore, the generated first maintenance instruction signal directly translates these physical causes into actionable human-machine prompts. This signal can manifest as a text alarm box on the monitoring terminal screen, or as an audible and visual alarm, SMS notification, or push notification to the maintenance management system. Its purpose is to prevent operators from wasting time on process parameters when an anomaly has been determined to be of physical damage type, and instead guide them directly to perform targeted inspections and replacements of the most likely fault points, thereby shortening troubleshooting time and ensuring the production line quickly returns to normal. The first maintenance instruction signal may also include recommended inspection steps, such as "Please stop the machine to check the integrity of the filter and clean the nozzles."

[0109] If the minimum current value is not lower than the preset minimum current threshold, meaning the current drop depth is still within the preset shallow range, but the recovery time is still abnormally shorter than the standard recovery time, it indicates that the faster system recovery speed is not caused by severe physical damage, but more likely by deviations in process parameters, such as an overall high hydroentangling pressure setting or fluctuations in the fiber web feeding speed. These factors may slightly speed up the system response, but not to the point of causing a deep current drop. Therefore, this type of anomaly is classified as a second type of anomaly.

[0110] Optionally, when a second type of anomaly is confirmed, a second maintenance indication signal is generated to indicate the water jet pressure setting.

[0111] If the minimum current value is not lower than the preset minimum current threshold, meaning the current drop depth is still within the normal range, but the recovery time is still less than the standard recovery time, it is identified as a "Type II anomaly". The monitoring terminal then executes S402, generating another indication signal with different content.

[0112] The physical meaning of the second type of anomaly is fundamentally different from that of the first type, which is understandable. The absence of an abnormally deep drop in current indicates that the physical pathways such as the dewatering tank filter and nozzles are likely intact, without sudden damage or severe blockage. However, the shortened recovery time still suggests a change in the system's dynamic characteristics. This type of change is more likely due to deviations in process operation variables. Among these, the setpoint of the hydroentanglement pressure is one of the most critical influencing factors. The hydroentanglement pressure determines the energy input for fiber entanglement. If the pressure setpoint is unknowingly increased, the fiber web will be fully entangled in a shorter time, altering the dewatering characteristics and resulting in the system recovering to normal current levels more quickly after the active disturbance ends. Additionally, deviations in the pressure setpoint may also be caused by pressure sensor drift or control system errors, but regardless of the cause, the result is an overall acceleration of the response curve, without a sharp drop in current.

[0113] Therefore, the second maintenance instruction signal focuses on the hydraulic pressure setpoint. This signal, also transmitted via screen, alarm lights, or information system, aims to guide operators to first check for abnormalities in process parameters, rather than directly disassembling and inspecting the equipment hardware. This helps differentiate the nature of the problem, reduces unnecessary downtime, and improves maintenance efficiency.

[0114] Through this classification indication, the first and second maintenance signals form a complete hierarchical diagnostic output. Furthermore, the second maintenance indication signal can also prompt checks on other process parameters such as the web feed rate or the vacuum setting of the hydroentanglement machine.

[0115] Optionally, in order to enable the benchmark for anomaly determination to be automatically adjusted along with the equipment aging process and to avoid misuse of the standard recovery time due to normal equipment aging and time-varying characteristics, the method may also include S114~S116:

[0116] S114: Obtain the cumulative operating parameters of the spunlace nonwoven fabric production line.

[0117] Understandably, during real-time monitoring of the production process, in addition to reading the current operating speed in real time, the monitoring terminal also needs to obtain a cumulative amount, i.e., cumulative operating parameters, from the production line's control system, counter, or production management system to characterize the historical usage of the equipment.

[0118] The parameter reflects the total load or total working time experienced by the spunlace nonwoven fabric production line since it was put into operation or since the last replacement or overhaul of a key component. It can take various forms, such as the cumulative number of hours the equipment has been running, the cumulative total length, weight, or number of rolls of nonwoven fabric produced, or a comprehensive indicator composed of weighted combinations of these quantities. The purpose of obtaining this parameter is to quantify the degree of physical changes that gradually accumulate in the equipment due to long-term operation, including the progressive clogging of the vacuum dehydration chamber filter, minor wear of the high-pressure pump and pipelines of the spunlace machine, and normal wear such as slow corrosion of the nozzles. These changes are slow and inevitable, and they gradually alter the system's fluid dynamics characteristics, thereby affecting the dynamic response speed of the vacuum dehydration chamber motor current to pressure disturbances. For example, the cumulative operating parameter can be read directly from the cumulative operating time register of the PLC or obtained from the cumulative production data of the MES system, in units of hours or tons.

[0119] S115: Based on the cumulative operating parameters, the standard recovery time is corrected to obtain the dynamic standard recovery time.

[0120] Understandably, the standard recovery time obtained from the preset data is essentially the fastest current recovery capability exhibited by the equipment under a relatively new, non-aging, and fault-free baseline condition. This value is a static baseline and does not account for the natural drift in response characteristics after normal aging of the equipment.

[0121] As accumulated operating parameters increase, even without any faults, the system's recovery time may change directionally. For example, partial filter blockage may alter the vacuum system's inertia, slightly increasing or decreasing the recovery time. Ignoring this normal drift and continuing to use a fixed standard recovery time as the basis for judging anomalies may lead to misjudging normal aging-related recovery time deviations as abnormalities, resulting in false alarms. Alternatively, actual faults after aging may cause changes in recovery time that fail to exceed the original threshold, leading to missed alarms.

[0122] Therefore, in this step, the accumulated operating parameters are used as input, and the original static standard recovery time is adjusted according to certain logic to output a dynamic standard recovery time that matches the current cumulative usage level of the equipment. The dynamic value can track the normal evolution of the equipment's health status and always represents the fastest normal recovery level that the system can achieve under the current aging level. The specific correction method can be function mapping, table lookup, or calculation based on empirical formulas. Regardless of the method used, the core concept is to quantify aging with accumulated operating parameters and use the aging amount to shift the judgment benchmark, making subsequent anomaly judgments more consistent with the actual physical state of the equipment.

[0123] For example, step S115 may include the following steps:

[0124] S1151: Based on the cumulative running parameters, query the preset degradation mapping relationship to obtain the degradation coefficient, where the degradation coefficient is a positive number less than or equal to 1.

[0125] The degradation mapping relationship is determined by fitting historical recovery time data of the spunlace nonwoven fabric production line under different cumulative operating parameters and without any abnormalities in the production process. The degradation coefficient monotonically decreases with increasing cumulative operating parameters. Specifically, the cumulative operating parameters of the spunlace nonwoven fabric production line, such as cumulative operating time or cumulative output, quantify the total usage load experienced by the equipment from its initial state to the current moment. This step uses this cumulative operating parameter to find a corresponding coefficient value from a pre-established degradation mapping relationship; this coefficient is named the degradation coefficient.

[0126] The degradation mapping relationship is a set of data correspondences pre-stored in the monitoring terminal's memory, which maps the values ​​of cumulative operating parameters to a corresponding degradation coefficient. This mapping relationship can take many forms, such as a data lookup table that lists several discrete cumulative operating parameter nodes, such as cumulative operating hours of 100 hours, 500 hours, 1000 hours, etc., and the corresponding degradation coefficient value for each node.

[0127] It can also be a mathematical function expression, using the accumulated operating parameters as independent variables, and directly calculating the degradation coefficient after substituting them into the function. Regardless of the form, the essence is to transform the concept of "how long it has been in reserve or how much has been produced" into a specific numerical factor that can be used to correct the standard recovery time.

[0128] The degradation coefficient is limited to a positive number less than or equal to 1, meaning its value ranges between (0,1). This limitation has a clear physical meaning: a degradation coefficient of 1 indicates that the equipment is in exactly the same condition as the initial baseline, and no perceptible normal aging has occurred; a degradation coefficient less than 1 indicates that the equipment's response characteristics have changed to varying degrees due to normal wear, progressive clogging, etc., and this change requires adjusting the original standard recovery time downwards. That is, after multiplying by a coefficient less than 1, the dynamic standard recovery time becomes smaller to accommodate changes in the equipment's recovery capability that may occur during use. Therefore, the degradation coefficient effectively quantifies the degree of equipment use as a percentage decrease in the original baseline value.

[0129] Understandably, by querying a preset degradation mapping relationship, the monitoring terminal can automatically obtain the degradation level corresponding to the current cumulative operating parameters. For example, the degradation mapping relationship can adopt a linear function α=1-k·T, where T is the cumulative operating time (hours) and k is the degradation rate constant (e.g., 0.0001 / hour); or an exponential model α=exp(-λT); or it can be based on an empirical table of multiple segments, for example: α=1.0 for 0~500 hours, α linearly decays to 0.85 for 500~2000 hours, and α=0.85 for more than 2000 hours.

[0130] S1152: Multiply the standard recovery time by the degradation factor to obtain the dynamic standard recovery time.

[0131] After obtaining the degradation coefficient, this step performs a multiplication operation to restore the time taken from the original standard determined by preset data based on the current running speed. Multiplying this by the degradation coefficient gives the dynamic standard recovery time. It can be written as a mathematical expression: = × Degradation coefficient.

[0132] Understandably, the original static standard recovery time represents the fastest current recovery capability of the equipment in a relatively new or baseline state, serving as the initial reference for the entire anomaly detection logic. However, after long-term cumulative operation, even without any faults, the dynamic characteristics of internal components such as pipes, filters, nozzles, and motors will shift due to normal wear and tear. The initial reference value can no longer accurately reflect the ultimate recovery capability under the current healthy state. A new reference value is obtained by multiplying the static reference value by a degradation factor calculated from actual usage history. This pulls the system to a level that matches its actual usage. It's no longer an ideal value for brand-new equipment, but rather the fastest recovery capability allowed by the system under current aging conditions. As an alternative, additive correction can also be used: = -ΔT, where ΔT is the offset determined based on accumulated running parameters, for example, obtained through a lookup table.

[0133] Therefore, if the recovery time is less than the standard recovery time, an anomaly is determined to have occurred in the production process, including:

[0134] S116: If the recovery time is less than the dynamic standard recovery time, then an anomaly has occurred in the production process.

[0135] After obtaining the dynamic standard recovery time, the actual recovery time will be... With this dynamic benchmark A comparison is made. Since the dynamic standard recovery time includes normal changes in the equipment due to cumulative operation, it more accurately characterizes the theoretically maximum recovery capability the system can exhibit in the current state than the static threshold. If the measured recovery time is smaller than this adaptive boundary, the system's dynamic response speed has exceeded the range that can be explained solely by normal aging, and there must be additional, abnormal physical state abrupt changes, such as sudden filter damage or sudden nozzle blockage. Therefore, [the following is a more accurate translation of the original text:] < The situation is judged as an abnormality in the production process, thus realizing a more accurate and reliable abnormality detection mechanism that can self-adjust with the equipment life cycle.

[0136] Based on the same inventive concept, please refer to Figure 2 This application also proposes a real-time monitoring system for the spunlace nonwoven fabric production process, including a monitoring terminal and a spunlace nonwoven fabric production line. The spunlace nonwoven fabric production line includes a vacuum dewatering chamber and a spunlace machine. The system also includes:

[0137] The first acquisition module is used to acquire the current operating speed of the spunlace nonwoven fabric production line;

[0138] The first determining module is used to determine the pressure disturbance amplitude, duration of action, and standard recovery time from preset data based on the current operating speed.

[0139] The generation module is used to generate a control signal based on the pressure disturbance amplitude and the duration of action. The control signal is configured to drive the hydroentanglement machine to make the hydroentanglement pressure change amplitude reach the pressure disturbance amplitude and the duration of action.

[0140] The data acquisition module is used to continuously acquire the current value of the motor in the vacuum dehydration box.

[0141] The second determining module is used to determine the time of output control signal as output time, and determine the end time based on the duration of action, and output control signal to hydroentanglement machine;

[0142] The third determination module is used to determine the time and current data points whose acquisition time is earlier than the output time in the time and current data points during the continuous acquisition process, and to determine the arithmetic mean of multiple current values ​​in the time and current data points as the reference current value.

[0143] The fourth determination module is used to divide all current values ​​from multiple continuous acquisitions by the reference current value to obtain multiple normalized current values.

[0144] The second acquisition module is used to acquire all time and current data points whose acquisition time is later than the end time, arrange them in chronological order, and compare the corresponding normalized current values ​​with the preset ratio threshold in turn, and take the acquisition time when the first acquisition time is lower than the preset ratio threshold as the recovery time.

[0145] The fifth determining module is used to determine the recovery time as the difference between the recovery time and the end time.

[0146] The sixth determination module is used to determine that an anomaly has occurred in the production process if the recovery time is less than the standard recovery time.

[0147] The modules described above can be functional units implemented in software and deployed on an industrial control computer or a cloud virtual server; alternatively, they can be partially or entirely implemented by hardware acceleration modules composed of application-specific integrated circuits (ASICs) or field-programmable gate arrays (FPGAs) to meet real-time requirements. Communication between modules can be achieved through shared memory, message queues, or network sockets.

[0148] Based on the same inventive concept, embodiments of this application also propose a processing apparatus, which includes:

[0149] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the real-time monitoring method for the spunlace nonwoven fabric production process according to the embodiments of this application.

[0150] In addition, to achieve the above objectives, embodiments of this application also propose a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the real-time monitoring method for the spunlace nonwoven fabric production process of embodiments of this application.

[0151] The following is combined Figure 3 A detailed description of each component of the processing equipment 300 is provided below:

[0152] The processor 301 is the control center of the processing device 300. It can be a single processor or a collective term for multiple processing elements. For example, the processor 301 can be one or more central processing units (CPUs), application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0153] Alternatively, the processor 301 can perform various functions of the processing device 300 by running or executing software programs stored in the memory 302 and by calling data stored in the memory 302.

[0154] In a specific implementation, as one example, processor 301 may include one or more CPUs, for example... Figure 3 CPU0 and CPU1 are shown in the diagram.

[0155] In a specific implementation, as one embodiment, the processing device 300 may also include multiple processors. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). Here, a processor may refer to one or more devices, circuits, and / or processing cores used for processing data (e.g., computer program instructions).

[0156] The memory 302 is used to store the software program that executes the solution of the present invention, and the processor 301 controls its execution. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0157] Optionally, the memory 302 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 302 may be integrated with the processor 301 or exist independently, and may be connected via the interface circuit of the processing device 300. Figure 3 (Not shown in the image) is coupled to processor 301, and this embodiment of the invention does not specifically limit this.

[0158] Transceiver 303 is used for communication with other processing devices. For example, if processing device 300 is a terminal, transceiver 303 can be used to communicate with a network device or with another terminal device. As another example, if processing device 300 is a network device, transceiver 303 can be used to communicate with a terminal or with another network device.

[0159] Alternatively, transceiver 303 may include a receiver and a transmitter. Figure 3 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0160] Optionally, the transceiver 303 can be integrated with the processor 301, or it can exist independently and be connected via the interface circuit of the processing device 300. Figure 3 (Not shown in the image) is coupled to processor 301, and this embodiment of the invention does not specifically limit this.

[0161] Understandable, Figure 3 The structure of the processing device 300 shown does not constitute a limitation on the processing device. The actual processing device may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0162] Furthermore, the technical effects of the processing device 300 can be referred to the technical effects of the methods in the above-described method embodiments, and will not be repeated here.

[0163] It should be understood that the processor in the embodiments of the present invention can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0164] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DRRAM). The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuitry), firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the flow or function according to embodiments of the present invention is produced. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., infrared, wireless, microwave, etc.) means. A computer-readable storage medium can be any available medium that a computer can access, or a data storage device such as a server or data center that includes one or more sets of available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives (SSDs).

[0165] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0166] In this invention, "at least one" refers to one or more items, and "more than one" refers to two or more items. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple. It should be understood that in various embodiments of this invention, the sequence number of the above processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this invention.

[0167] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

Claims

1. A method for real-time monitoring of the spunlace nonwoven fabric production process, characterized in that, A real-time monitoring system for a spunlace nonwoven fabric production process is provided. The system includes a monitoring terminal and a spunlace nonwoven fabric production line, which includes a vacuum dewatering chamber and a spunlace machine. The method is executed by the monitoring terminal and includes: Obtain the current operating speed of the spunlace nonwoven fabric production line; Based on the current operating speed, the pressure disturbance amplitude, duration of action, and standard recovery time are determined from preset data; A control signal is generated based on the pressure disturbance amplitude and the duration of action, wherein the control signal is configured to drive the hydroentanglement machine to make the hydroentanglement pressure change amplitude reach the pressure disturbance amplitude and continue for the duration of action; Start continuous acquisition of the motor current value of the vacuum dehydration box; The moment when the control signal is output is determined as the output moment, and the end moment is determined based on the duration of action, and the control signal is output to the hydroentanglement machine; In the continuous acquisition process, among the time and current data points, the time and current data points whose acquisition time is earlier than the output time are determined, and the arithmetic mean of multiple current values ​​in the time and current data points is determined as the reference current value. Divide all the current values ​​in the multiple continuous acquisitions by the reference current value to obtain multiple normalized current values; All time and current data points whose acquisition time is later than the end time are acquired, arranged in chronological order, and the corresponding normalized current values ​​are compared with a preset ratio threshold in turn. The acquisition time at which the first acquisition time is lower than the preset ratio threshold is taken as the recovery time. The difference between the recovery time and the end time is determined as the recovery time. If the recovery time is less than the standard recovery time, then an anomaly is determined to have occurred in the production process.

2. The method for real-time monitoring of the spunlace nonwoven fabric production process according to claim 1, characterized in that, Based on the current operating speed, the pressure disturbance amplitude, duration of action, and standard recovery time corresponding to the current operating speed are determined from preset data. The preset data is determined by the following steps: Obtain historical pressure and historical current values ​​of the spunlace nonwoven fabric production line when it is running at multiple different operating speeds; Based on the historical pressure value, multiple pressure fluctuation events are determined, wherein the pressure fluctuation event is an event in which the historical pressure value deviates from the steady state and recovers to the steady state, and the deviation of the historical pressure value exceeds a preset amplitude threshold. Based on the historical current value at the steady state before the fluctuation, the historical current value collected during the pressure fluctuation event is normalized to obtain the normalized historical current value corresponding to each pressure fluctuation event. The moment when the current returns to the steady state is taken as the target recovery start time, and the time from the target recovery start time when the normalized historical current value reaches the preset recovery threshold is obtained and determined as the target recovery time. The standard recovery time at the specified operating speed is determined based on the minimum value among all the target recovery times corresponding to the specified operating speed. The pressure disturbance amplitude corresponding to the operating speed is determined by the sum of the maximum deviation amplitude and the first preset additional value among all the pressure fluctuation events corresponding to the operating speed. The duration of action corresponding to the operating speed is determined by summing the maximum duration of pressure deviation among all pressure fluctuation events corresponding to the operating speed with a second preset additional value.

3. The method for real-time monitoring of the spunlace nonwoven fabric production process according to claim 1, characterized in that, After determining that an anomaly has occurred in the production process, the method further includes: The minimum value among all the normalized current values ​​obtained between the end time and the recovery time is determined as the lowest current value. Compare the minimum current value with a preset minimum current threshold. If the minimum current value is lower than the preset minimum current threshold, then a first type of anomaly is confirmed; otherwise, it is confirmed as a second type of anomaly.

4. The method for real-time monitoring of the spunlace nonwoven fabric production process according to claim 3, characterized in that, The preset minimum current threshold is obtained from the preset data based on the current operating speed, wherein the preset data further includes: When running at different operating speeds, the preset minimum current threshold is determined based on the historical minimum value of the normalized current value in historical normal pressure fluctuation events.

5. The method for real-time monitoring of the spunlace nonwoven fabric production process according to claim 3, characterized in that, The method further includes: When the first type of anomaly is confirmed, a first maintenance indication signal is generated to prompt the inspection of the filter screen of the vacuum dehydration tank and the nozzle of the hydroentanglement machine; When the second type of abnormality is confirmed, a second maintenance indication signal is generated to indicate the water jet pressure setting value.

6. The method for real-time monitoring of the spunlace nonwoven fabric production process according to claim 1, characterized in that, The method further includes: Obtain the cumulative operating parameters of the spunlace nonwoven fabric production line; Based on the accumulated operating parameters, the standard recovery time is corrected to obtain the dynamic standard recovery time; If the recovery time is less than the standard recovery time, then an anomaly is determined to have occurred in the production process, including: If the recovery time is less than the dynamic standard recovery time, then an anomaly is determined to have occurred in the production process.

7. The method for real-time monitoring of the spunlace nonwoven fabric production process according to claim 6, characterized in that, The cumulative operating parameters include cumulative operating time or cumulative output, and the correction of the standard recovery time includes: Based on the accumulated operating parameters, a preset degradation mapping relationship is queried to obtain the degradation coefficient, wherein the degradation coefficient is a positive number less than or equal to 1; The dynamic standard recovery time is obtained by multiplying the standard recovery time by the degradation coefficient.

8. The method for real-time monitoring of the spunlace nonwoven fabric production process according to claim 7, characterized in that, The degradation mapping relationship is determined by fitting historical recovery time data of the spunlace nonwoven fabric production line under different cumulative operating parameters and when no abnormalities occur in the production process. The degradation coefficient decreases monotonically with the increase of the cumulative operating parameters.

9. A real-time monitoring system for the production process of spunlace nonwoven fabric, characterized in that, The system includes a monitoring terminal and a spunlace nonwoven fabric production line, wherein the spunlace nonwoven fabric production line includes a vacuum dewatering tank and a spunlace machine, and the system also includes: The first acquisition module is used to acquire the current operating speed of the spunlace nonwoven fabric production line; The first determining module is used to determine the pressure disturbance amplitude, duration of action, and standard recovery time from preset data based on the current operating speed. A generation module is configured to generate a control signal based on the pressure disturbance amplitude and the duration of action, wherein the control signal is configured to drive the hydroentanglement machine to make the hydroentanglement pressure change amplitude reach the pressure disturbance amplitude and continue for the duration of action; The acquisition module is used to initiate continuous acquisition of the motor current value of the vacuum dehydration box; The second determining module is used to determine the time when the control signal is output as the output time, and to determine the end time based on the duration of action, and to output the control signal to the hydroentanglement machine. The third determining module is used to determine, in the time and current data points during the continuous acquisition process, the time and current data points whose acquisition time is earlier than the output time, and to determine the arithmetic mean of multiple current values ​​in the time and current data points as a reference current value. The fourth determining module is used to divide all the current values ​​in the multiple continuously acquired data by the reference current value to obtain multiple normalized current values; The second acquisition module is used to acquire all time and current data points whose acquisition time is later than the end time, arrange them in chronological order, and compare the corresponding normalized current values ​​with a preset ratio threshold in turn, and take the acquisition time when the first acquisition time is lower than the preset ratio threshold as the recovery time. The fifth determining module is used to determine the difference between the recovery time and the end time as the recovery time. The sixth determining module is used to determine that an abnormality has occurred in the production process if the recovery time is less than the standard recovery time.

10. A processing apparatus, characterized in that, The processing equipment includes: At least one processor; And, a memory communicatively connected to at least one of the processors; The memory stores instructions that can be executed by at least one of the processors, which are executed by at least one of the processors to enable the at least one of the processors to perform a real-time monitoring method for the production process of spunlace nonwoven fabric as claimed in any one of claims 1-8.