Method and system for monitoring textile processing progress
By using multi-scale permutation entropy and phase space reconstruction technology, the accuracy of textile processing progress monitoring has been improved, the prediction deviation caused by equipment instability has been solved, and more conservative production plan adjustments and fault early warnings have been achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-01-21
- Publication Date
- 2026-04-17
AI Technical Summary
Existing textile processing progress monitoring technologies suffer from large prediction deviations under complex working conditions, failing to accurately reflect the actual output efficiency of equipment, leading to production plan deviations and unstable equipment operation.
By collecting operating speed data of textile equipment, multi-scale arrangement entropy analysis and phase space reconstruction are performed to calculate the microscopic disorder and phase space trajectory deviation, generating an effective working time correction coefficient, correcting the instantaneous measured speed to obtain a more accurate remaining processing time, and issuing anomaly warnings.
It improves the accuracy of remaining processing time prediction, reduces the statistical error of working hours caused by equipment downtime or low-speed creep, ensures the continuity and stability of production, and triggers early warnings in a timely manner to reduce the generation of defective products.
Smart Images
Figure CN121879305A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of industrial automation control technology. More specifically, this invention relates to a method and system for monitoring the progress of textile processing. Background Technology
[0002] In the modern textile printing and dyeing industry, refined management of production planning is crucial for shortening delivery cycles. Accurate monitoring of processing progress is a prerequisite for achieving intelligent production scheduling and dynamic dispatch. In actual production scenarios, equipment such as stenters typically operate continuously according to order lengths. The management system needs to monitor progress in real time and estimate the remaining completion time to coordinate subsequent logistics or finishing processes. If the prediction is inaccurate, it will lead to process disconnection, resulting in the accumulation of semi-finished products or equipment idling and waiting.
[0003] Existing monitoring technologies typically rely on rotary encoders to collect mechanical rotation pulses and calculate instantaneous operating speed by counting the number of pulses per unit time. Traditional remaining time prediction often uses linear extrapolation, which involves directly dividing the current instantaneous speed by the remaining length of the order, or setting a fixed speed threshold to simply determine whether the equipment is in working condition.
[0004] However, the aforementioned technologies have limitations under complex working conditions. On the one hand, textile equipment often experiences frequent transient starts and stops or low-speed creep due to tension fluctuations or mechanical jams. These non-steady-state signals often fluctuate around the speed threshold, causing existing technologies to misclassify them and introduce statistical bias in effective working hours. On the other hand, traditional methods ignore the nonlinear impact of operational stability on output efficiency. Although the average value of frequent speed fluctuations may be close to the set value, the actual output efficiency will decrease due to mechanical losses during acceleration and deceleration, resulting in a large deviation between the predicted remaining time and the actual completion time. Moreover, this deviation will accumulate as processing continues, making it difficult to meet production scheduling requirements. Summary of the Invention
[0005] To address the aforementioned technical problem of large deviations in completion time prediction, the present invention provides solutions in the following aspects.
[0006] In a first aspect, the present invention provides a method for monitoring the progress of textile processing, comprising: The raw linear velocity data of the textile equipment is collected and preprocessed to obtain a preprocessed operating speed time series. Multi-scale permutation entropy analysis is performed on the operating speed time series to obtain permutation entropy values at multiple scales. Based on the normalized average of the permutation entropy values, the micro-disorder of the operating speed time series is determined. Phase space reconstruction is performed on the operating speed time series to obtain multiple phase space state vectors. The distance between the phase space state vectors and the preset ideal attractor center vector is calculated to obtain the phase space trajectory deviation of the operating speed time series. A weighted correction is applied to the operating micro-disorder and the phase space trajectory deviation to obtain an effective working time correction coefficient. The instantaneous measured speed is corrected using the effective working time correction coefficient to obtain the remaining processing time of the textile equipment, which is then uploaded to the management system. The operating micro-disorder is compared with a preset disorder threshold for anomaly warning.
[0007] This invention assesses the irregular fluctuations of equipment on a microscopic time scale and the degree of deviation of the macroscopic operating trajectory from the ideal steady state by evaluating operational micro-disorder and phase space trajectory deviation, respectively. It utilizes operational micro-disorder and phase space trajectory deviation to obtain effective time correction coefficients and numerically corrects instantaneous measured speeds, thereby obtaining a production speed closer to actual output capacity. This reduces statistical errors in time caused by equipment downtime or low-speed creep, ensuring that the calculated remaining processing time includes potential efficiency losses, making it more conservative and accurate than linear extrapolation based solely on physical speed. By comparing operational micro-disorder with a preset threshold, an early warning is triggered when equipment process stability decreases, prompting maintenance personnel to check yarn tension or lubrication, reducing defective products and ensuring the controllability of textile processing progress.
[0008] Preferably, obtaining the preprocessed running speed time series includes: An incremental photoelectric rotary encoder is installed on the main drive shaft or the end of the speed measuring roller of the textile equipment. It is connected to an industrial control computer or programmable logic controller through a high-speed pulse counting module. The sampling frequency is set, and the pulse frequency fed back by the incremental photoelectric rotary encoder is read in real time through an industrial fieldbus. The pulse frequency is then converted into a running linear speed signal according to the diameter of the speed measuring roller. A sliding window is set for the running linear velocity signal. The arithmetic mean of the running linear velocity signal within the sliding window is calculated as the effective velocity value at the corresponding time. The effective velocity values at each time are arranged in chronological order to obtain the preprocessed running velocity time series.
[0009] This invention installs incremental photoelectric rotary encoders on key parts of textile equipment and sets up a sliding window to smooth the acquired pulse frequency, filtering out electromagnetic noise interference from frequency converters and motors in the industrial environment, while retaining transient speed fluctuation characteristics that reflect the stability of mechanical operation. By calculating the arithmetic mean within the sliding window as the effective speed value, the signal-to-noise ratio of the data is improved, and reliable data support is provided for subsequent nonlinear dynamic feature extraction. This reduces the risk of misjudgment caused by glitches in the original signal and ensures that the operating speed time series truly reflects the physical operating condition of the textile equipment.
[0010] Preferably, the degree of operational micro-disorder satisfies the following relation: ; In the formula, The degree of operational micro-disorder represents the time series of operating speeds; Indicates the maximum scale factor; Represents scale factor The entropy value of the arrangement; This represents the optimal embedding dimension required to reconstruct the phase space; Represents the factorial symbol; This represents the natural logarithm function.
[0011] Preferably, obtaining the permutation entropy value includes: The preprocessed running speed time series is coarsened at different scale factors to obtain a coarsened sequence with a total number equal to the maximum scale factor. For the coarsened sequence at any scale factor, the probability distribution of the numerical arrangement pattern of the reconstructed vector of the coarsened sequence is statistically analyzed, and the arrangement entropy value at the corresponding scale factor is calculated.
[0012] Preferably, obtaining the optimal embedding dimension includes: Based on the nonlinear characteristics of the running speed time series, the optimal embedding dimension required to reconstruct the phase space is calculated using the pseudo nearest neighbor algorithm. and time delay .
[0013] Preferably, the phase space trajectory deviation satisfies the following relationship: ; In the formula, This represents the phase space trajectory deviation of the running speed time series; This represents the total number of state vectors in the phase space; Represents the first phase in the reconstructed phase space Each phase space state vector; Represents the center vector of an ideal attractor; The symbol for the Euclidean norm of a vector.
[0014] This invention obtains the phase space trajectory deviation, which characterizes the instantaneous deviation of the operating state of textile equipment from the ideal optimal working condition at a specific moment, by calculating the Euclidean distance between the state vector in the reconstructed phase space and the center vector of the ideal attractor. By accumulating and calculating the deviation energy over the entire observation period, it assesses whether the equipment has performance drift at the macroscopic level due to mechanical wear or insufficient lubrication, thereby reflecting the consistency and stability of equipment operation and making up for the insufficiency of single-time dimension analysis in revealing the system evolution trajectory.
[0015] Preferably, obtaining the phase space state vector includes: Based on the optimal embedding dimension And time delay, using the delay coordinate method to map the running speed time series to In 3D phase space, generation A phase space state vector.
[0016] Preferably, the effective working hours correction factor satisfies the following relationship: ; In the formula, This represents the effective working hours correction factor; This represents the weighting factor for micro-level influences; The degree of operational micro-disorder represents the time series of operating speeds; Indicates the macroeconomic deviation weighting factor; This represents the phase space trajectory deviation of the running speed time series; This indicates the set standard processing speed.
[0017] This invention introduces a micro-influence weighting factor and a macro-deviation weighting factor. It weights and fuses the micro-disorder of operation with the phase space trajectory deviation after normalization by standard processing speed to generate an effective working time correction coefficient. This allows for adjusting the proportion of the impact of micro-vibration and macro-drift on production capacity according to the specific needs of textile processes. It also transforms the physical measurement speed into an effective production speed that reflects the actual output loss. Furthermore, when the equipment is simultaneously affected by both micro-vibration and macro-drift, it can reasonably assess the efficiency of converting physical speed into effective production capacity, reducing the deviation caused by directly using physical speed for prediction.
[0018] Preferably, the step of correcting the instantaneous measurement speed using an effective working time correction coefficient to obtain the remaining processing time of the textile equipment and uploading it to the management system; comparing the operating micro-disorder degree with a preset disorder threshold for anomaly warning, includes: The total length of textiles to be processed as specified in the order is subtracted from the length already processed as measured by the current sensor. This subtracted length is then divided by the product of the instantaneous measured speed at the current moment in the operating speed time series and the effective working time correction coefficient, plus a preset small value. This yields the corrected remaining processing time for the textile equipment. The remaining processing time is then uploaded to the management system via a network interface for adjusting the production schedule. Simultaneously, a disorder threshold is set. If the micro-disorder of the operating speed time series exceeds the disorder threshold, an early warning signal is triggered, prompting maintenance personnel to check the yarn tension or mechanical lubrication.
[0019] This invention utilizes the corrected effective production speed to perform a division operation on the remaining processing volume, obtaining the remaining processing time that includes potential downtime risks. This fully considers the efficiency reduction caused by unsteady operation, making the corrected remaining processing time of the textile equipment more conservative and in line with the actual production rhythm. By uploading the remaining processing time to the management system, it assists the scheduler in dynamically adjusting the production schedule of subsequent processes, and can also reduce the situation of disconnection between upstream and downstream processes. At the same time, it uses the early warning signal triggered when the micro-disorder of operation exceeds the threshold to help maintenance personnel quickly locate potential fault points such as yarn tension or mechanical lubrication and ensure the continuity of production.
[0020] Secondly, the present invention provides a monitoring system for the progress of textile processing, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned method for monitoring the progress of textile processing is implemented.
[0021] By adopting the above technical solution, a computer program for monitoring the progress of textile processing is generated and stored in a memory so that it can be loaded and executed by a processor. This allows for the creation of a terminal device based on the memory and processor, making it convenient to use.
[0022] The beneficial effects of this invention are as follows: By collecting high-frequency operating data of textile equipment and combining it with nonlinear dynamic analysis technology, this invention improves the problem of insufficient prediction accuracy of traditional linear monitoring methods when facing non-steady-state conditions such as equipment micro-stops or low-speed creep. This invention utilizes multi-scale permutation entropy to assess the disordered fluctuations of equipment at the microscopic level, and combines phase space reconstruction technology to obtain the macroscopic deviation of the equipment's operating trajectory from the ideal steady state. This allows for the analysis of potential dynamic factors affecting textile processing efficiency at different scales. By converting the microscopic disorder and phase space trajectory deviation into effective working time correction coefficients, this invention corrects the physical measurement speed to an effective production speed that reflects actual output losses. This reduces the calculation deviation of remaining processing time introduced by yarn tension fluctuations or process drift, making the estimated completion time fed back to the management system more consistent with the actual production rhythm. This helps production schedulers dynamically adjust subsequent process plans and reduce disconnections between upstream and downstream processes. Simultaneously, the use of disorder indicators to trigger early warnings of faults ensures the continuity and stability of the textile printing and dyeing process. Attached Figure Description
[0023] Figure 1 The flowchart illustrates a method for monitoring the progress of textile processing according to the present invention. Figure 2 A schematic diagram illustrating the time series of the original running linear velocity; Figure 3 This diagram illustrates the time series of the preprocessed running speed. Figure 4 The diagram illustrates the analysis results of permutation entropy values at multiple scales. Detailed Implementation
[0024] This invention discloses a method for monitoring the progress of textile processing, referring to... Figure 1 This includes steps S100-S400: S100: Collect the raw linear speed data of the textile equipment and preprocess it to obtain the preprocessed operating speed time series.
[0025] It should be noted that since the operating status of textile equipment is directly reflected in the speed changes of the main shaft or key drive rollers, and considering the complex electromagnetic environment in industrial settings, and the fact that speed fluctuations of textile equipment on a microscopic time scale often contain information reflecting mechanical and process stability, low-frequency sampling or simple pulse counting cannot capture these transient characteristics. Therefore, this invention employs a high-frequency sampling strategy to acquire the original signal and performs targeted denoising processing, thereby improving the signal-to-noise ratio of the data and providing data support for subsequent nonlinear feature extraction.
[0026] Specifically, an incremental photoelectric rotary encoder is installed on the main drive shaft or the end of the speed measuring roller of the textile equipment, and connected to an industrial control computer or programmable logic controller via a high-speed pulse counting module. A sampling frequency is set, and the pulse frequency fed back by the incremental photoelectric rotary encoder is read in real time via an industrial fieldbus. The pulse frequency is then converted into a linear speed signal based on the diameter of the speed measuring roller. For example, the sampling frequency is 100Hz to ensure that speed fluctuations at the 10ms level can be captured.
[0027] For example, Figure 2 This is a time series diagram of the original operating linear velocity. The data in the middle section of the time axis shows non-periodic and violent fluctuations, which indicates that the textile equipment has non-steady-state operating characteristics on a micro-time scale.
[0028] It should be noted that, in order to suppress the interference of electromagnetic noise generated by the frequency converter and motor on the signal, the acquired raw running linear speed signal is subjected to moving average filtering.
[0029] A sliding window is set for the running linear velocity signal. The arithmetic mean of the running linear velocity signal within the sliding window is calculated as the effective velocity value at the corresponding time. The effective velocity values at each time are arranged in chronological order to obtain the preprocessed running velocity time series. For example, the sliding window length is 5 sampling points.
[0030] For example, Figure 3 This is a schematic diagram of the preprocessed operating speed time series. The original signal was smoothed by a sliding window to filter out high-frequency noise interference, while retaining the transient fluctuation characteristics that reflect changes in the stability of mechanical operation.
[0031] Thus, the preprocessed runtime time series was obtained.
[0032] S200. Perform multi-scale permutation entropy analysis on the running speed time series to obtain permutation entropy values at multiple scales; determine the running micro-disorder of the running speed time series based on the normalized average of the permutation entropy values; reconstruct the running speed time series in phase space to obtain multiple phase space state vectors, calculate the distance of the phase space state vectors relative to the preset ideal attractor center vector, and obtain the phase space trajectory deviation of the running speed time series.
[0033] It should be noted that since the micro-stops or low-speed creep phenomena of textile equipment exhibit random fluctuations in the time-domain waveform, traditional variance or standard deviation statistics are insufficient to distinguish this potentially deterministic nonlinear dynamic behavior from pure background noise. Considering that permutation entropy can assess the complexity of local numerical patterns in time series, and that multi-scale analysis can reveal the microstructural characteristics of the system from different time resolutions, this invention introduces multi-scale permutation entropy to assess the microscopic complexity of the equipment's operating state, thereby reducing the risk of misjudging non-steady-state process fluctuations as normal operating noise.
[0034] Specifically, the micro-level disorder of the running speed time series is calculated based on the running speed time series, including: Based on the nonlinear characteristics of the running speed time series, the optimal embedding dimension required for reconstructing the phase space is calculated using the phase space reconstruction parameter determination method. and time delay For example, the method for determining the phase space reconstruction parameters is the false nearest neighbor algorithm, which is existing technology and will not be described in detail here.
[0035] Set the maximum scale factor Exemplary To cover the main frequency band of equipment mechanical vibration.
[0036] The preprocessed runtime time series at different scale factors The following were subjected to coarse-graining treatment to obtain A coarse-grained sequence; for the scale factor The coarse-grained sequence is analyzed, and the probability distribution of the numerical arrangement patterns of the reconstructed vectors of the coarse-grained sequence is statistically distributed. The scaling factor is then calculated. The permutation entropy value It should be noted that the range of values for the scaling factor is [range missing]. .
[0037] For example, Figure 4 This is a schematic diagram of the analysis results of permutation entropy values under multiple scales. The curves show the changes in permutation entropy values of the preprocessed running speed time series at different time resolutions as the scale factor increases.
[0038] The degree of micro-disorder in the running speed time series satisfies the following relationship: ; In the formula, The degree of operational micro-disorder represents the time series of operating speeds; Indicates the maximum scale factor; Represents scale factor The entropy value of the arrangement; This represents the optimal embedding dimension required to reconstruct the phase space; Represents the factorial symbol; This represents the natural logarithm function.
[0039] In this relation, This represents the normalized single-scale permutation entropy, used to reduce the influence of embedding dimension on the entropy magnitude, and characterizes the speed of the time series at different scale factors. Local complexity. This represents the cumulative sum of the normalized permutation entropy of the operating speed time series across all scale factors, characterizing the overall microscopic disorder of the operating speed time series across multiple scales. A greater degree of overall microscopic disorder indicates a more complex and disordered permutation pattern at the microscopic level in the operating speed time series, reflecting frequent non-periodic starts, stops, or vibrations in the textile equipment; conversely, a smaller degree of overall microscopic disorder indicates smoother equipment operation and higher predictability of speed changes.
[0040] Thus, the microscopic disorder of the running speed time series was obtained.
[0041] It should be noted that since the microscopic disorder of the operating speed time series mainly focuses on high-frequency local fluctuations, and the textile production process also involves long-term performance drift caused by mechanical wear, insufficient lubrication, or changes in roll diameter, such macroscopic trend changes are difficult to intuitively reflect in a single-dimensional time series. Considering that phase space reconstruction technology can map a one-dimensional time series to a high-dimensional state space, thereby revealing the complete dynamic trajectory of system evolution, and that deviations from the system state will manifest as changes in the distance between the reconstructed trajectory and the ideal attractor, this invention evaluates the degree of deviation of the overall operating state of the equipment from the standard process by calculating the phase space trajectory deviation of the operating speed time series, thereby improving the ability to assess the macroscopic operating stability of the equipment.
[0042] Preferably, the present invention calculates the phase space trajectory deviation of the running velocity time series based on the reconstructed phase space state vector, including: Based on the optimal embedding dimension and time delay The phase space reconstruction method is used to map the running speed time series to... In 3D phase space, generation Each phase space state vector. It should be noted that... ,in, Indicates the length of the running speed time series; Indicates the embedding dimension; This indicates a time delay. For example, the phase space reconstruction method is the delayed coordinate method, which is existing technology and will not be elaborated upon here.
[0043] Set the ideal attractor center vector For example, the ideal attractor center vector is obtained by collecting the speed data of the device in its best operating condition when it is brand new or has just been maintained, and calculating its geometric center after reconstructing the phase space.
[0044] The phase space trajectory deviation of the running speed time series satisfies the following relationship: ; In the formula, This represents the phase space trajectory deviation of the running speed time series; This represents the total number of state vectors in the phase space; Represents the first phase in the reconstructed phase space Each phase space state vector; Represents the center vector of an ideal attractor; The symbol for the Euclidean norm of a vector.
[0045] In this relation, Indicates the first The Euclidean distance between the phase space state vector and the center vector of the ideal attractor characterizes the instantaneous deviation of the operating state of the textile equipment at a specific moment from the ideal steady state. This represents the comprehensive deviation energy of the operating velocity time series over the reconstructed trajectory in the entire phase space. The larger the comprehensive deviation energy, the more significant the divergence or drift of the device's operating trajectory relative to the ideal state over the entire observation period, reflecting macroscopic operational instability. Conversely, the smaller the comprehensive deviation energy, the more closely the device's operating trajectory revolves around the ideal center, reflecting high consistency and stability in the device's operation.
[0046] Thus, the phase space trajectory deviation of the running speed time series was obtained.
[0047] S300. The microscopic disorder and phase space trajectory deviation of the operation are weighted and corrected to obtain the effective working time correction coefficient.
[0048] It should be noted that since the instantaneous speed measured by physical measurements cannot be fully converted into effective production capacity when the equipment is operating in a non-steady state, frequent acceleration and deceleration fluctuations will cause the actual output efficiency to be lower than the theoretical calculation value based on physical speed. Considering that the operational micro-disorder and phase space trajectory deviation reflect the operational stability of the equipment from the two dimensions of micro-jitter and macro-drift, respectively, the higher the values of the operational micro-disorder and phase space trajectory deviation indices, the greater the loss of effective output per unit time. Therefore, this invention introduces correction coefficients for calculating effective working time based on operational micro-disorder and phase space trajectory deviation to numerically correct the physical speed, thereby obtaining an effective production speed that is closer to the actual output capacity and reducing the prediction error of remaining time caused by relying solely on physical speed.
[0049] Specifically, this invention calculates the effective working time correction coefficient based on the microscopic disorder and phase space trajectory deviation of the operating speed time series, including: Set the weighting factor for micro-influence and macroeconomic deviation weighting factor Exemplary , This study focuses on the impact of micro-fluctuations on textile processes.
[0050] The effective working hours correction factor satisfies the following relationship: ; In the formula, This represents the effective working hours correction factor; This represents the weighting factor for micro-level influences; The degree of operational micro-disorder represents the time series of operating speeds; Indicates the macroeconomic deviation weighting factor; This represents the phase space trajectory deviation of the running speed time series; This indicates the set standard processing speed, which is obtained from the process parameters of the production order.
[0051] In this relation, This indicates the degree of negative impact of high-frequency jitter at the micro level on effective production capacity. The larger the value, the more severe the non-steady-state fluctuations of the equipment on a microscopic time scale, and the greater its contribution to the loss of working hours; conversely, the smaller the value, the more severe the non-steady-state fluctuations of the equipment on a microscopic time scale, and the greater its contribution to the loss of working hours. The smaller the value, the more stable the equipment's microscopic operation. This indicates the degree of negative impact of process drift at the macro level relative to standard production speed. The larger the value, the more serious the deviation of the overall equipment operating state from the ideal process, resulting in a higher loss of effective output; conversely, The smaller the value, the closer the equipment's macroscopic operating state is to the standard setting. This represents the total discount factor when converting physical measurement speed into effective production speed. The greater the total discount factor, the more the equipment is affected by both micro-vibration and macro-drift, resulting in a lower efficiency in converting physical speed into effective output. Conversely, the smaller the total discount factor, the more stable the equipment operation, with almost all physical speed being converted into effective production capacity.
[0052] Thus, the effective working hours correction factor was obtained.
[0053] S400: Correct the instantaneous measurement speed using the effective working time correction coefficient, obtain the remaining processing time of the textile equipment and upload it to the management system; compare the operating micro-disorder with the preset disorder threshold to provide anomaly warning.
[0054] It should be noted that traditional remaining time prediction methods ignore the nonlinear degradation of long-term output efficiency caused by declining equipment health, leading to significant discrepancies between predicted and actual completion times. Furthermore, abnormal increases in operational micro-disorder often imply early risks of abnormal yarn tension or mechanical lubrication failure. Considering that the effective working time correction coefficient can assess capacity loss based on equipment dynamics, and that independent monitoring of disorder can pinpoint process anomalies, this invention calculates the remaining time using the corrected speed and sets a threshold for real-time monitoring. This provides a more conservative completion time estimate that includes potential downtime or inefficiency risks, thus enabling proactive alerts for abnormal operating conditions.
[0055] Specifically, the remaining processing time of the textile equipment is calculated based on the effective working time correction factor, and the remaining processing time satisfies the following relationship: ; In the formula, Indicates the remaining processing time of the textile equipment after the correction; Indicates the total length of textiles to be processed as specified in the order; This indicates the cumulative processed length currently measured by the sensor; This represents the instantaneous measured velocity at the current moment in the running speed time series; This represents the effective working hours correction factor; It is a preset microvalue used to prevent the denominator from being 0, and can be set to 0.001.
[0056] In this relation, This represents the converted effective production rate, which is used in division operations by substituting the physical rate for the effective production rate. Calculated It will be greater than or equal to the theoretical time obtained by linear calculation based solely on instantaneous speed measurement, thus yielding a more conservative completion time.
[0057] This gives us the remaining processing time for the corrected textile equipment.
[0058] The revised remaining processing time of the textile equipment is uploaded to the management system via a network interface for dynamic adjustment of the production schedule for subsequent processes. Simultaneously, a disorder threshold is set; if the micro-disorder of the operating speed time series exceeds the threshold, an early warning signal is triggered, prompting maintenance personnel to check yarn tension or mechanical lubrication.
[0059] This completes the monitoring of the textile processing progress.
[0060] This invention also discloses a monitoring system for textile processing progress, including a processor and a memory. The memory stores computer program instructions, which, when executed by the processor, implement a method for monitoring textile processing progress according to the present invention.
[0061] The system also includes other components well known to those skilled in the art, such as communication buses and communication interfaces, the settings and functions of which are known in the art and will not be described in detail here.
[0062] While this specification has shown and described numerous embodiments of the invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will occur to those skilled in the art without departing from the spirit and essence of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in the practice of this invention.
Claims
1. A method for monitoring the progress of textile processing, characterized in that, include: The raw linear velocity data of the textile equipment is collected and preprocessed to obtain the preprocessed time series of the operating velocity. Multi-scale permutation entropy analysis was performed on the running speed time series to obtain permutation entropy values at multiple scales; Based on the normalized average value of the permutation entropy, the micro-disorder of the running speed time series is determined; the running speed time series is reconstructed in phase space to obtain multiple phase space state vectors, and the distance between the phase space state vectors and the preset ideal attractor center vector is calculated to obtain the phase space trajectory deviation of the running speed time series. The operational micro-disorder and phase space trajectory deviation are weighted and corrected to obtain the effective working time correction coefficient. The instantaneous measurement speed is corrected using an effective working time correction factor to obtain the remaining processing time of the textile equipment and upload it to the management system. The micro-level disorder is compared with the preset disorder threshold to provide anomaly warning.
2. The method for monitoring the progress of textile processing according to claim 1, characterized in that, The acquisition of the preprocessed running speed time series includes: An incremental photoelectric rotary encoder is installed on the main drive shaft or the end of the speed measuring roller of the textile equipment. It is connected to an industrial control computer or programmable logic controller through a high-speed pulse counting module. The sampling frequency is set, and the pulse frequency fed back by the incremental photoelectric rotary encoder is read in real time through an industrial fieldbus. The pulse frequency is then converted into a running linear speed signal according to the diameter of the speed measuring roller. A sliding window is set for the running linear velocity signal. The arithmetic mean of the running linear velocity signal within the sliding window is calculated as the effective velocity value at the corresponding time. The effective velocity values at each time are arranged in chronological order to obtain the preprocessed running velocity time series.
3. The method for monitoring the progress of textile processing according to claim 1, characterized in that, The operational micro-disorder degree satisfies the following relation: ； In the formula, The degree of operational micro-disorder represents the time series of operating speeds; Indicates the maximum scale factor; Represents scale factor The entropy value of the arrangement; This represents the optimal embedding dimension required to reconstruct the phase space; Represents the factorial symbol; This represents the natural logarithm function.
4. A method for monitoring the progress of textile processing according to claim 1 or 3, characterized in that, The acquisition of the permutation entropy value includes: The preprocessed running speed time series is coarsened at different scale factors to obtain a coarsened sequence with a total number equal to the maximum scale factor. For the coarsened sequence at any scale factor, the probability distribution of the numerical arrangement pattern of the reconstructed vector of the coarsened sequence is statistically analyzed, and the arrangement entropy value at the corresponding scale factor is calculated.
5. The method for monitoring the progress of textile processing according to claim 3, characterized in that, Obtaining the optimal embedding dimension includes: Based on the nonlinear characteristics of the running speed time series, the optimal embedding dimension required to reconstruct the phase space is calculated using the pseudo nearest neighbor algorithm. and time delay .
6. The method for monitoring the progress of textile processing according to claim 1, characterized in that, The phase space trajectory deviation satisfies the following relationship: ； In the formula, This represents the phase space trajectory deviation of the running speed time series; This represents the total number of state vectors in the phase space; Represents the first phase in the reconstructed phase space Each phase space state vector; Represents the center vector of an ideal attractor; The symbol for the Euclidean norm of a vector.
7. A method for monitoring the progress of textile processing according to claim 1 or 5, characterized in that, The acquisition of the phase space state vector includes: Based on the optimal embedding dimension And time delay, using the delay coordinate method to map the running speed time series to In 3D phase space, generation A phase space state vector.
8. The method for monitoring the progress of textile processing according to claim 1, characterized in that, The effective working hours correction factor satisfies the following relationship: ； In the formula, This represents the effective working hours correction factor; This represents the weighting factor for micro-level influences; The degree of operational micro-disorder represents the time series of operating speeds; Indicates the macroeconomic deviation weighting factor; This represents the phase space trajectory deviation of the running speed time series; This indicates the set standard processing speed.
9. A method for monitoring the progress of textile processing according to claim 1, characterized in that, The instantaneous measurement speed is corrected using an effective working time correction coefficient to obtain the remaining processing time of the textile equipment and upload it to the management system. The system compares the operational micro-disorder level with a preset disorder threshold to provide anomaly warnings, including: The total length of textiles to be processed as specified in the order is subtracted from the length already processed as measured by the current sensor. This subtracted length is then divided by the product of the instantaneous measured speed at the current moment in the operating speed time series and the effective working time correction coefficient, plus a preset small value. This yields the corrected remaining processing time for the textile equipment. The remaining processing time is then uploaded to the management system via a network interface for adjusting the production schedule. Simultaneously, a disorder threshold is set. If the micro-disorder of the operating speed time series exceeds the disorder threshold, an early warning signal is triggered, prompting maintenance personnel to check the yarn tension or mechanical lubrication.
10. A monitoring system for the progress of textile processing, characterized in that, include: A processor and a memory, the memory storing computer program instructions that, when executed by the processor, implement a method for monitoring the progress of textile processing according to any one of claims 1-9.