Polyester blended fabric production process tracing information management method

Abstract

The invention relates to the technical field of production traceability, in particular to a polyester blended fabric production process traceability information management method, which comprises the following steps: acquiring batch jump nodes, analyzing structure and tension sudden change frequency, identifying dense inflection point sections, associating equipment start-stop behaviors, and constructing a traceability node registration form. According to the method, the jump index table is constructed by synchronously analyzing the starting and stopping states of the process nodes and the tension feedback, so that the batch interruption points can be accurately identified, and the accurate positioning of the abnormal section of the process is realized. By combining the multipoint slope trend in tension feedback and the time synchronization analysis of the structure image, the cooperative relationship between the fiber arrangement and the torque change can be disclosed, and the potential abnormal window can be quickly marked. By means of corresponding analysis of tension fluctuation and structure disturbance frequency, source tracing of causes of abnormal fluctuation is facilitated. Layered clustering is carried out on dense tension inflection point areas, inflection point distribution density is quantified, and a high-risk process section can be highlighted in a dynamic tension fluctuation sequence.

Description

Technical Field

[0001] The invention relates to the technical field of production tracing, and in particular to a method for managing production process tracing information of polyester blended fabrics. Background Art

[0002] The field of production traceability technology includes the collection, recording and management of relevant information of products in production, processing, transportation and other links, in order to achieve systematic control of product sources and flows. The core content of this technology field includes raw material information identification, production batch information association, process node information tracking and finished product status information integration. Through data collection devices, information coding methods and database construction, key information of the entire product life cycle is systematically managed.

[0003] Among them, the traceability information management method for the production process of polyester blended fabrics refers to the information recording and management method for polyester blended fabrics in specific processes such as spinning, weaving, dyeing and finishing, including the management of raw material ratio information, production process node information, processing equipment status information, time sequence information of each process and operator responsibility information, and synchronizes the above information to the central information system by setting unified coding rules and information entry procedures.

[0004] Although existing technologies cover raw material ratios, process nodes and operation records, most of them rely on single-dimensional information registration and lack the ability to judge the linkage between material batch changes and equipment behavior. When a process abnormality occurs, it is impossible to trace the causal relationship between tension fluctuations, structural variations and equipment start-up and stop, resulting in post-judgment of emergencies based on static data. The traceability granularity is rough, and positioning ambiguity or misjudgment often occurs. Taking batch interruption as an example, the current technology only records the point where the interruption occurs, but does not judge its interference effect on the downstream structural arrangement or tension state, making it difficult to form a full-link data closed loop. In addition, tension feedback and image sequence data have not been included in the unified time series analysis system, resulting in the dynamic relationship between fiber arrangement abnormality and mechanical response not being captured, making process adjustments more dependent on experience judgment, affecting the accuracy of traceability and the real-time response. For example, when a tension curve shows abnormal fluctuations, the existing system often cannot determine whether it is caused by the sudden start-up and stop of the preceding equipment, and lacks the corresponding sequence jump risk level judgment mechanism, which ultimately leads to the failure to timely identify and intervene in the abnormal process section. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a polyester blended fabric production process traceability information management method.

[0006] In order to achieve the above object, the present invention adopts the following technical scheme: a polyester blended fabric production process traceability information management method, comprising the following steps: S1: Obtain the continuous process nodes on the polyester blend production line, capture the node indices with discontinuous node batch sequences, and establish a start-stop tension batch jump index table; S2: According to the start-stop tension batch jump index table, set the jump section as a fixed detection window, calculate the arrangement level spacing slope of multiple consecutive points in the window, and mark the window at the mutation position according to the slope direction of multiple points to obtain the fiber level and torque mutation position set; S3: Based on the marked mutation position time periods in the fiber level and torque mutation position set, count the amplitude change frequencies in each time period, select the interaction response area according to the change frequencies, and generate a tension fluctuation synchronization section; S4: Based on the time periods recorded in the tension fluctuation synchronization section and locate the positions where the inflection points appear, group and cluster the densities of all sections by calculating the inflection point density to generate a tension inflection point dense section; S5: According to the inflection point peak section in the tension inflection point dense section, match the start-stop status records of the corresponding equipment, and establish a polyester blend fabric process traceability node registration form by screening the risk sections and corresponding process nodes in the start-stop status records.

[0007] As a further solution of the present invention, the start-stop tension batch jump index table includes a jump node position index, a corresponding tension feedback index segment, a batch continuity interruption identifier, and a start-stop time interval status identifier. The fiber level and torque mutation position set includes a mutation detection window position, a level spacing slope change direction, a torque flip marker, and a mutation node identification number. The tension fluctuation synchronization section is specifically a trajectory perturbation amplitude distribution section, a tension switching frequency segment, a frequency coincidence marking interval, and a synchronization response identification number. The tension inflection point dense section includes a tension peak grouping label, a section density statistic, a dense grouping index number, and a response center time interval. The polyester blend fabric process traceability node registration form includes a risk jump sequence section position, a jump sequence grade score value, a registered process node number, and a traceability grade classification label.

[0008] As a further solution of the present invention, the obtaining steps of the start-stop tension batch jump index table are specifically as follows: S111: Obtain the start-stop time sequence, material batch sequence, and tension feedback time stamp sequence of the continuous process nodes on the polyester blend production line, arrange the start-stop times of each node in the order of the process flow, calculate the interval between the start-stop times of adjacent nodes in turn, and determine whether the adjacent intervals are zero to obtain a set of start-stop time adjacent zero interval nodes; S112: Divide the tension feedback timestamp sequence according to the time period corresponding to each node in the set of adjacent zero-interval nodes of the start-stop time, extract the tension feedback time section corresponding to the start-stop time, extract the material batch sequence within the corresponding section, compare the numbers of the material batch sequence in the front-back order, determine whether there is a number jump in the batch sequence, and obtain the list of batch jump nodes in the tension time section; S113: Call the list of batch jump nodes in the tension time section to perform cross-judgment with the set of adjacent zero-interval nodes of the start-stop time, screen the node indexes that simultaneously have a start-stop time of zero and discontinuous material batches, and generate the start-stop tension batch jump index table.

[0009] As a further solution of the present invention, the steps for obtaining the fiber layer and torque mutation position set are specifically as follows: S211: According to the time period position recorded in the start-stop tension batch jump index table, extract the fiber axial arrangement image sequence, adjacent layer spacing value sequence, and torque direction symbol sequence of the corresponding drafting section and twisting section process sections, perform time synchronization processing, extract the matching structure data section, and generate the structure sequence synchronization data set; S212: Based on the structure sequence synchronization data set, set the structure sequence within the jump section as an equal-width fixed detection window, and use the formula: ; Calculate the normalized slope change rate of the detection window , and construct the standard slope change trend value sequence within the window with the change rate as an index; wherein, represents the change amount of the layer spacing in the th segment, represents the time change amount corresponding to the th segment, represents the reference amplitude of the layer spacing in the whole section, represents the reference amplitude of the time difference in the whole section, and represents the number of spacing point pairs in the window; S213: Call each window segment in the standard slope change trend value sequence, judge whether the change trend of the window segment is a discontinuous fluctuation, and detect whether there is a reverse flip flag in the corresponding torque direction symbol sequence, screen the positions where there are both inconsistent directions and symbol flips, mark the screened window positions, and obtain the fiber layer and torque mutation position set.

[0010] As a further solution of the present invention, the steps for obtaining the tension fluctuation synchronization section are specifically as follows: S311: Based on the fiber hierarchy and the marked mutation time periods concentrated at the torque mutation positions, extract the fiber arrangement trajectory path sequence and the tension fluctuation value sequence within the corresponding time periods, calculate the unit time displacement amplitude difference of the trajectory path in the axial direction respectively, and count the amplitude change frequency within each time segment. At the same time, perform symbol recognition on the tension fluctuation sequence and count the positive and negative value switching frequency within the same time period to obtain a structure and tension change frequency data comparison table; S312: Call the trajectory change frequency and the tension switching frequency in the structure and tension change frequency data comparison table, divide the time axis into segments and set a fixed interval, and judge whether the two types of frequencies simultaneously exceed their respective average reference values for each time slice, screen the overlapping segments where the fluctuation behaviors appear simultaneously in the time position, and summarize them in chronological order to establish a tension fluctuation synchronization segment.

[0011] As a further solution of the present invention, the obtaining steps of the tension inflection point dense segment are specifically as follows: S411: Based on the time segments in the tension fluctuation synchronization segment, extract the corresponding tension change sequence, locate all local extreme points in the sequence, divide the tension sequence into continuous segments according to the fixed time slice width, count the number of inflection points in each time segment respectively, and generate a tension inflection point number distribution table; S412: Call the inflection point number value, time span, tension standardized fluctuation amplitude and extreme value change rate of each segment in the tension inflection point number distribution table, perform time dimension normalization and unit amplitude unification processing, and use the formula: ; Calculate the inflection point density of the current th time segment to obtain a tension inflection point density sequence; Among them, represents the number of inflection points in the current segment, represents the time length corresponding to the current segment, represents the unit time fluctuation standard deviation square of the tension sequence within the current segment, represents the tension extreme value difference within the current segment, represents the number of inflection points in the previous time segment , represents the tension extreme value difference in the previous time segment ; S413: According to the density in the tension inflection point density sequence, hierarchically cluster all segments according to the density, identify the group to which the density peak belongs, and judge whether it constitutes a continuous segment fragment on the time axis. If the density values within the continuous segment are all higher than the set density determination threshold, record the corresponding segment position to obtain the tension inflection point dense segment.

[0012] As a further solution of the present invention, the specific steps for obtaining the process traceability node registration form of the polyester blended fabric are as follows: S511: According to the inflection point peak section in the tension inflection point dense section, match the equipment start-stop state records, extract the start-stop records of the corresponding equipment at the time points before and after the section, calculate the time interval between the previous start-stop and the next start-stop, and count the number of skipped equipment nodes in the current process section. Determine whether the number of skipped nodes exceeds the skip sequence number threshold and whether the start-stop time interval is within the preset start-stop abnormal section range. Screen the satisfied process sections as abnormal process sections and generate a risk skip sequence process section list. S512: Call the skip sequence node number and start-stop time interval data of each process section in the risk skip sequence process section list, and use the formula: ; Calculate the skip sequence level score of the process section and integrate to obtain a skip sequence level score sequence. Among them, represents the number of skip sequence nodes of the target process section, represents the maximum number of skip sequence nodes in all process sections, represents the start-stop time interval of the target process section, represents the average value of the start-stop time intervals of all process sections; S513: According to the score of each process section in the skip sequence level score sequence, set a skip sequence risk score threshold, screen all the score values, retain the process section nodes with scores higher than the score threshold, combine and register the process numbers, score values and corresponding time position information of the nodes, and connect them to the structural path of the blended fabric traceability system to establish a process traceability node registration form for the polyester blended fabric.

[0013] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In the present invention, by synchronously analyzing the start-stop state of the process node and the tension feedback, a jump index table is constructed, which can accurately identify the batch break points and achieve precise positioning of the abnormal section of the process. By combining the multi-point slope trend in the tension feedback and the time synchronization analysis of the structural image, the cooperative relationship between the fiber arrangement and the torque change can be revealed, and potential abnormal windows can be quickly marked. By means of the corresponding analysis of the tension fluctuation and the frequency of the structural disturbance, the screening of the behavior coincidence period is realized, which helps to trace the cause of the abnormal fluctuation. By performing hierarchical clustering on the dense tension inflection point region and quantifying the inflection point distribution density, the high-risk process sections can be highlighted in the dynamic tension fluctuation sequence. By performing a linkage analysis of the start-stop record and the skip nodes, and combining the dual indicators of the skip level score and the start-stop interval, high-risk nodes can be extracted and registered for tracing. This processing logic integrates the multi-dimensional cross-comparison between the time-axis synchronization, the structural dynamic analysis and the equipment start-stop behavior, enabling the association between the microscopic changes and the macroscopic control behavior in the textile process, thereby realizing the precise tracing of abnormal phenomena and the marking of responsible nodes, significantly improving the granularity and response efficiency of the tracing system, reducing the abnormal recognition delay, and increasing the information integration density and the decision-making response speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a schematic diagram of the main steps of the present invention; Figure 2 is a flowchart of step S1 of the present invention; Figure 3 is a flowchart of step S2 of the present invention; Figure 4 is a flowchart of step S3 of the present invention; Figure 5 is a flowchart of step S4 of the present invention; Figure 6 is a flowchart of step S5 of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0015] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0016] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0017] Please refer to Figure 1 , the present invention provides a technical solution: a method for managing traceability information of the production process of a polyester blended fabric, including the following steps: S1: Obtain continuous process nodes on the polyester blending production line, capture the node indexes with discontinuous node batch sequences, and establish a start-stop tension batch jump index table; S2: According to the start-stop tension batch jump index table, set the jump section as a fixed detection window, calculate the arrangement level spacing slope of multiple consecutive points in the window, and mark the window at the mutation position according to the slope direction of multiple points to obtain the fiber level and torque mutation position set; S3: Based on the marked mutation position time periods in the fiber level and torque mutation position set, count the amplitude change frequencies in each time period, select the interactive response area according to the change frequencies, and generate a tension fluctuation synchronization section; S4: Based on the time periods recorded in the tension fluctuation synchronization section and locate the positions where the inflection points appear. By calculating the inflection point density, group and cluster the densities of all sections to generate a tension inflection point dense section; S5: According to the inflection point peak section in the tension inflection point dense section, match the start-stop state records of the corresponding equipment, and establish a polyester blended fabric process traceability node registration form by screening the risk sections and corresponding process nodes in the start-stop state records; The start-stop tension batch jump index table includes the jump node position index, the corresponding tension feedback index segment, the batch continuity interruption identifier, and the start-stop time interval status identifier. The fiber level and torque mutation position set includes the mutation detection window position, the change direction of the level spacing slope, the torque flip marker bit, and the mutation node identification number. The tension fluctuation synchronization section is specifically the trajectory perturbation amplitude distribution section, the tension switching frequency segment, the frequency coincidence marker interval, and the synchronization response identification number. The tension inflection point dense section includes the tension peak grouping label, the section density statistic, the dense grouping index number, and the response center time interval. The polyester blended fabric process traceability node registration form includes the risk jump sequence section position, the jump sequence grade score value, the registered process node number, and the traceability grade classification label.

[0018] Please refer to Figure 2 , the steps for obtaining the start-stop tension batch jump index table are specifically as follows: S111: Obtain the start-stop time series, material batch sequence, and tension feedback timestamp sequence of consecutive process nodes on the polyester blended production line. Arrange the start-stop times of each node in the order of the process flow, calculate the intervals between the start-stop times of adjacent nodes in turn, and determine whether the adjacent intervals are zero to obtain the set of nodes with adjacent zero intervals in start-stop times; To obtain the start-stop time series, material batch sequence, and tension feedback timestamp sequence of consecutive process nodes on the polyester blended production line, it is necessary to record the operating status of each process equipment in the drawing section, drafting section, and twisting section based on the equipment data acquisition system. Assume that there are 3 nodes in each of the drawing section, drafting section, and twisting section, and the collected start-stop times are as follows: Node A1 starts at 08:00 and ends at 08:05, Node A2 starts at 08:05 and ends at 08:10, Node A3 starts at 08:10 and ends at 08:15. Then compare the start-stop time differences between adjacent nodes: The difference between the start-stop time of A2 and the start-stop time of A1 is 0 minutes, which is judged as a coincidence in start-stop time. Here, it is necessary to calculate the start-stop time intervals between adjacent nodes group by group in order and represent them in minutes. During the execution process, calculate the difference between the start-stop times of each pair of adjacent nodes respectively. If the difference is 0, it is marked as adjacent start-stop time being zero. After collecting the time difference results between multiple nodes, it is necessary to mark the start-stop interval status between each node in a boolean manner. For example, A1 - A2 is TRUE, A2 - A3 is FALSE, indicating that A1 and A2 have a zero interval, while A2 and A3 do not have a zero interval. Finally, mark all the nodes in the TRUE state and output the node numbers to obtain the set of nodes with adjacent zero intervals in start-stop times.

[0019] S112: According to the time periods corresponding to each node in the set of nodes with adjacent zero intervals in start-stop times, divide the tension feedback timestamp sequence and extract the tension feedback time segments corresponding to the start-stop times. Extract the material batch sequence within the corresponding segments, compare the numbers of the material batch sequence in the front-back order, determine whether there is a number jump in the batch sequence, and obtain the list of batch jump nodes in the tension time segment; According to each pair of node time ranges in the set of nodes with adjacent start and stop times being zero, the tension feedback timestamp sequence is divided into multiple sub-sections. The matching principle is that the tension data time range needs to cover the start and stop times of the corresponding start and stop periods. For example, if the start and stop times of nodes A1 - A2 are 08:00 - 08:10, then the data corresponding to the time period from 08:00 to 08:10 in the tension sequence is extracted. The tension feedback data can be collected at a frequency of once per second. In this time period, a total of 10 minutes × 60 seconds = 600 sampling points are obtained. At the same time, the material batch number in this time period is extracted. For example, if the batch numbers are from B1 → B3 → B2, then the sequence is judged for numbering. If the sequence number shows a rollback (such as B2 after B3) or a cross-segment jump (such as B3 after B1), it is judged that the numbering is discontinuous. The specific judgment criterion is to convert the batch number into an equally spaced natural number sequence for difference processing. For example, B1 → B3 → B2 is mapped to 1 → 3 → 2. The differences between adjacent terms are 2 and -1. Since the difference is not 1, it is judged as discontinuous numbering, and then this section is marked as a batch jump. Repeat this process to traverse all time periods with start and stop being zero, and finally summarize them into a list of batch jump nodes in the tension time section.

[0020] S113: Call the list of batch jump nodes in the tension time section to perform cross-judgment with the set of nodes with adjacent zero-interval start and stop times, screen the node indexes that have both start and stop times being zero and discontinuous material batches, and generate a start-stop tension batch jump index table; Perform cross-screening on the list of batch jump nodes in the tension time section and the set of nodes with adjacent start and stop times being zero, and extract the nodes that meet the two conditions, that is, the start and stop time interval is zero and the batch sequence number is discontinuous. For example: the start and stop time interval of nodes A2 and A3 is 0, and the batch numbers they process are B3 → B1. Converted to a natural sequence, it is 3 → 1, and the difference is -2. The jump is established. Mark this node as a valid abnormal node. At the same time, collect and organize the numbers of all nodes that meet this dual condition, number them in chronological order and assign index values. The output results need to include fields such as the start and end time periods corresponding to each jump node, the material batch number, the number difference, and whether it is a jump mark. The content recorded in the finally established index table is as follows: node A2, time 08:05 - 08:10, batch sequence B3 → B1, number difference is -2, jump mark is 1. After screening all nodes, they are summarized into a set of abnormal node index data, which is the start-stop tension batch jump index table.

[0021] Please refer to Figure 3 , the steps for obtaining the fiber layer and torque mutation position set are specifically as follows: S211: According to the time period positions recorded in the start-stop tension batch jump index table, extract the fiber axial arrangement image sequences, adjacent layer spacing value sequences, and torque direction symbol sequences of the corresponding drafting section and twisting section process zones, perform time synchronization processing, extract the matching structural data segments, and generate a structural sequence synchronization data set; Extract the fiber axial arrangement image sequences, layer spacing value sequences, and torque direction symbol sequences in the drafting section and twisting section process zones. The image sequences are collected in real time from the production zone by an optoelectronic imaging device at a high frame rate (e.g., 20 frames per second) at the process site. The size of each frame of the image is set to pixels, record the fiber axial arrangement state, obtain the fiber arrangement trajectory contour through image edge extraction, use the maximum gradient edge gray difference method to determine the boundary points between adjacent layers in the image, extract the pixel distance between adjacent layers in each frame of the image, and convert it to millimeters to form a layer spacing sequence. For the image frame , if the four boundary point coordinates extracted from it are respectively , then the spacing value sequence is pixels, and the corresponding physical spacing is millimeters. The torque direction is deduced from the fiber rotation direction in the image, that is, use the curvature direction extraction algorithm for the trajectory curve to obtain the rotation positive and negative polarities of the torque for each frame. If the positive and negative signs alternate in consecutive frames, such as frame is positive (+1), frame is negative (-1), then it is judged that a direction flip has occurred. Finally, the image data of this time period is converted into: a fiber structure trajectory image sequence, a layer spacing numerical sequence, and a torque direction symbol sequence, and integrated into one under the same time index to obtain a structural parameter extraction result set.

[0022] S212: Based on the structural sequence synchronization data set, set the structural sequence within the jump section as an equal-width fixed detection window, and use the formula: ; Calculate the normalized slope change rate of the detection window , and construct a standard slope change trend value sequence within the window with the change rate as an index; Among them, represents the change in layer spacing of the th segment, represents the change in time corresponding to the th segment, represents the reference amplitude of the layer spacing of the entire section, represents the reference amplitude of the time difference of the entire section, represents the number of spacing point pairs in the window.

[0023] Set the jump segment as a fixed detection window, for example, each window length is 0.5 seconds, the corresponding image frame number is 10 frames, and extract the three-point spacing sequence and the corresponding timestamp data from it. The original spacing unit is millimeter and the time unit is second. In order to eliminate the influence of unit differences, all participating items need to be normalized. Assume that the spacing of three consecutive levels in a window changes to mm, corresponding to the time change of seconds, the base level spacing of the acquisition section is mm, time base is seconds, then the normalized slope change rate The calculation is done using the following formula: ; The data is calculated as follows: ; It indicates the intensity of fiber level spacing change per unit time within a certain detection window. Its physical meaning is the rate of change of the amplitude of fiber structure disturbance within the window. The larger the value, the more drastic the change of fiber arrangement within the window and the more unstable the structure. This indicator comprehensively considers the relative proportional relationship between the spacing change and the sampling time resolution, and uniformly measures the degree of disturbance between different windows under the unit normalization scale. This value can be used as a direct basis for judging the significance of structural disturbance, and provides a quantitative basis for the direction and amplitude of structural fluctuations for subsequent abnormal node identification and mutation segment screening, and plays a key role in trend identification.

[0024] Repeat the above calculation process in all detection windows to form a normalized slope change value sequence corresponding to the window, which is used as the perturbation index in the segment to judge the intensity of the dynamic perturbation behavior of each window, and then generate a standard slope change trend value sequence. The formula is beneficial in that by introducing a normalized denominator, data of different scales are reduced to a unified scale, improving the stability and accuracy of cross-segment perturbation comparison.

[0025] S213: calling each window segment in the standard slope change trend value sequence, determining whether the window segment change trend is non-continuous fluctuation, and detecting whether there is a reverse flip sign in the corresponding torque direction symbol sequence, screening positions with both inconsistent directions and flipped signs, marking the screened window positions, and obtaining a fiber level and torque mutation position set; Call each window segment in the standard slope change trend value sequence to determine whether the slope change direction is continuous and consistent in the three-point sequence. Specifically, if the three-segment normalized slope change rate sequence is , indicating that the direction changes from rising to falling and then rising again, and the directions are inconsistent. Then match the sign change of the window at the corresponding time point in the torque direction symbol sequence. If the segment symbol is , it indicates that a reversal has occurred. The window that meets these two conditions is the mutation window and is marked. For example, in the detection section, if the direction of window 5 is inconsistent and torque reversal also occurs, then the window number 5 is added to the marked set. Finally, the window index that meets the dual determination is output to form the fiber hierarchy and torque mutation position set, and this result is used to identify the discontinuous nodes of the fiber structure and match with the tension fluctuation logic chain. This result shows that: Synchronous perturbation windows have been screened out from both the slope change and torque flip aspects and can be directly used for the subsequent identification of structural misalignment behavior.

[0026] Please refer to Figure 4 , the steps for obtaining the tension fluctuation synchronous section are specifically as follows: S311: Based on the marked mutation time periods in the fiber hierarchy and torque mutation position set, extract the fiber arrangement trajectory path sequence and tension fluctuation value sequence within the corresponding time periods. Calculate the unit time displacement amplitude difference of the trajectory path in the axial direction respectively, and count the amplitude change frequency within each time section. At the same time, perform symbol recognition on the tension fluctuation sequence and count the positive and negative value switching frequency within the same time period to obtain the structural and tension change frequency data comparison table; First, extract the fiber arrangement trajectory path sequence and tension fluctuation value sequence corresponding to this time period. The fiber arrangement trajectory path can be identified by the pixel displacement of consecutive edge points in the axial direction in the structure image and arranged in chronological order. The tension fluctuation value sequence is collected by the tension sensors in the drafting section and the twisting section at the corresponding timestamps. The unit time displacement of the structure trajectory in the axial direction can be expressed as the change in the center of gravity of the pixel centers of two consecutive image frames divided by the frame time interval. For example, if the center positions of two consecutive frames are 145 pixels and 151 pixels respectively, and the frame time interval is 0.04 seconds, then the displacement rate is (151 - 145) / 0.04 = 150 px / s. The identification of the positive and negative switching frequency of the tension fluctuation requires segmenting and judging the positive and negative value transformation sections of the consecutive values in the tension value sequence in a sliding window manner. If a section of the tension sequence is [18, 20, -15, -17, 14, -12], then there are three positive and negative flips at 18→ -15, -17→14, and 14→ -12 respectively. Therefore, the tension fluctuation frequency within this time period is 3 times. After completing the statistics of the trajectory displacement frequency and the tension positive and negative switching frequency, align them to the same time reference. By judging whether the trajectory perturbation frequency and the tension switching frequency increase simultaneously within the same section, it is determined whether they constitute a synchronous response. In the example, if the trajectory displacement frequency in a certain section exceeds 5 times per second, the tension fluctuation frequency exceeds 3 times per second, and both occur in the time interval of 2 to 4 seconds, then this section is regarded as a synchronous response segment. All segments that meet the above conditions will be collected and output as the final result of the tension fluctuation synchronous section.

[0027] S312: Call the trajectory change frequency and tension switching frequency in the structure and tension change frequency data comparison table, divide the time axis into sections with a fixed interval, and for each time slice, respectively determine whether the two types of frequencies simultaneously exceed their respective average reference values. Screen the overlapping segments where the fluctuation behaviors appear simultaneously in terms of time position, summarize them in chronological order, and establish the tension fluctuation synchronization section; Call the structure and tension change frequency data comparison table, divide the time axis into equal intervals, with each section being 5 seconds. For each time window, extract the trajectory displacement change frequency and tension symbol switching frequency respectively. Set the reference value of the trajectory change frequency to 12 times / window, and the reference value of the tension switching frequency to 2 times / window. This value is obtained by averaging the normal fluctuation behaviors in 20 sample windows. Taking a single sample as an example, in window t1, the trajectory change frequency is 16 times, and the tension switching frequency is 3 times, both exceeding their reference values. Therefore, it is determined that window t1 is a synchronous fluctuation section. Subsequently, continuous identification processing is performed on the segments that meet this condition within all time periods. If two or more consecutive sections are synchronous segments, then mark this segment as an overlapping response segment. Finally, establish an index table structure with the time index as the unit. For example, time windows t1 - t3, t7 - t8 are overlapping response sections, indicating that there is a synchronous amplification behavior between the trajectory disturbance and the tension change within this section, and obtain the tension fluctuation synchronization section.

[0028] Please refer to Figure 5 , and the steps for obtaining the tension inflection point dense section are specifically as follows: S411: Based on the time segments in the tension fluctuation synchronization section, extract the corresponding tension change sequence, locate all local extreme points in the sequence, divide the tension sequence into continuous sections according to the fixed time slice width, respectively count the number of inflection points in each time section, and generate a tension inflection point number distribution table; Based on the recorded time segment in the tension fluctuation synchronization segment, in actual applications, the corresponding tension change signals need to be synchronously expanded along the time axis. Combining with the original data sequence output by the tension sensor, the tension signal is continuously sampled with a millisecond-level resolution. For example, monitoring the tension for 30 consecutive seconds at a frequency of 100 Hz can obtain 3000 tension sampling points. By calculating the first-order difference, the fluctuation direction between each point and its adjacent point in the sequence is judged, and then the position of the extreme point is determined. When the tension value changes from increasing to decreasing or from decreasing to increasing and meets the set extreme value threshold change amplitude (such as the change amplitude exceeds 1.5 N), it can be marked as an inflection point. Suppose the tension sampling sequence in a certain segment is: {52, 54, 56, 55, 53, 51, 53, 56, 59, 61, 60, 58, 55}, where the 4th position (56→55) and the 12th position (61→60) can be used as the wave peaks, and then the inflection point positions are determined to be 4 and 12. After performing the same rule detection on the entire 30-second sequence, the detected inflection points are assigned to each 10-second time segment. Suppose there are 6 inflection points in the first segment, 9 in the second segment, 5 in the third segment, and 12 in the fourth segment. This operation process can be embedded in production monitoring to reflect the distribution of tension disturbance points in real time and generate a tension inflection point quantity distribution table.

[0029] S412: Call the inflection point quantity value, time span, tension standardized fluctuation amplitude, and extreme value change rate of each segment in the tension inflection point quantity distribution table, and perform time dimension normalization and unit amplitude unification processing. Use the formula: ; Calculate the inflection point density of the current th time segment , and obtain the tension inflection point density sequence; Among them, represents the number of inflection points in the current segment, represents the corresponding time length of the current segment, represents the unit time fluctuation standard deviation square of the tension sequence within the current segment, represents the tension extreme value difference within the current segment, represents the number of inflection points in the previous time segment , represents the tension extreme value difference in the previous time segment , and all parameters are unified in the dimension of unit time to ensure the overall dimensional consistency. The density value is used as a quantitative index for the disturbance aggregation degree of the segment.

[0030] Call the inflection point numerical value and tension characteristic fluctuation value in the tension inflection point quantity distribution table. It is necessary to perform unified normalization processing on the indicators in all segments. Normalize the tension inflection point quantity , tension extreme value difference , tension variance , Time span Substitute into the formula for inflection point density calculation. The calculation steps are as follows: Taking the second section as an example, the number of inflection points , Time length , Tension extreme value difference , The previous section , Square value of the standard deviation of tension fluctuation , Number of inflection points in the previous section , According to the formula ; Obtain the tension density , The result shows that there is intensive disturbance behavior in this section per unit time. If this value is compared with the density judgment reference value of 2.8, it can be confirmed that it meets the judgment conditions. The descriptions of each parameter are as follows: is the number of inflection points in the current section, obtained from the inflection point statistical process, is the time span of the current section, set to 10 seconds, is the square value of the standard deviation of tension within the section, obtained by taking the square after calculating the sample standard deviation, is the difference between the maximum and minimum values in the tension sequence, is the difference between the extreme value ranges of two adjacent sections, is the difference in the number of inflection points between two sections, all normalized by time to express the disturbance fluctuation intensity. The benefit of this formula is that by integrating the tension fluctuation amplitude and the adjacent change rate, a three-dimensional description of short-term disturbances is carried out to generate a tension inflection point density sequence.

[0031] S413: According to the density in the tension inflection point density sequence, all sections are stratified and clustered by density, identify the group to which the density peak belongs, and judge whether it constitutes a continuous section segment on the time axis. If the density values within the continuous section are all higher than the set density judgment threshold, record the corresponding section position to obtain the tension inflection point intensive section; According to the values obtained in the tension inflection point density sequence, it is necessary to analyze each section's Perform clustering and recognition operations on the values. First, sort them in ascending order of density values and divide them into three groups: low-density group, medium-density group, and high-density group. Among them, the low-density group is the section where the density value is between 0.0 and 1.5. This range reflects the relatively sparse number of disturbance inflection points per unit time or the gentle change of tension fluctuation, often corresponding to the stable tension operation or weak interference period in the production process. The medium-density group corresponds to the section where the density value is greater than or equal to 1.5 and less than or equal to 2.8. This interval is the transition area from the stable disturbance state to the significant disturbance state. The high-density group is the section where the density value is greater than 2.8. In this group, the tension disturbance has the characteristics of frequent inflection point changes and severe tension fluctuations. For example, in the previous example, the calculated value of the second section is 3.115, so it is classified into the high-density group. Subsequently, combine the continuous sections in all high-density groups and judge whether they are continuous on the time axis and whether the density values all meet the set density threshold of greater than 2.8. Suppose the second section and the third section , then the two form a continuous section, record its start and end time range as 20 - 40 seconds, finally extract the position of this section as the dense disturbance response area, mark it as the core concern area, and obtain the tension inflection point dense section.

[0032] Please refer to Figure 6 , the steps for obtaining the polyester blended fabric process traceability node registration form are specifically as follows: S511: According to the inflection point peak section in the tension inflection point dense section, match the equipment start-stop state records, extract the start-stop records of the corresponding equipment at the time points before and after the section, calculate the time interval between the previous start-stop and the next start-stop, and count the number of skipped equipment nodes in the current process section. Judge whether the number of skipped nodes exceeds the skip sequence number threshold and whether the start-stop time interval is within the preset start-stop abnormal section range. Screen the satisfied process sections as abnormal process sections and generate a risk skip sequence process section list; First, retrieve the time intervals covered by the inflection point dense section in sequence according to the timestamps, and split the log data of all device operating states within this time period by device number to obtain the start and stop time points of each device before and after the section. For example, if the section occurs between 13:00 and 13:45 on June 13, 2024, and device A stops running at 12:55 and restarts at 13:47, the start and stop time interval is 52 minutes. This process corresponds to the start and stop time calculation step. Subsequently, identify the device nodes that do not appear in the start and stop records within the section time range, and count the number of nodes skipped in the logical sequence. For example, if the process section should pass through nodes A→B→C→D→E in sequence, but only nodes A and E appear in the start and stop records, the number of skipped nodes is 3, namely B, C, and D. If the number of skipped nodes exceeds the threshold and the start and stop time interval is within the abnormal section (for example, the preset abnormal start and stop interval is set to be greater than 30 minutes), then it is determined that the current process section constitutes a risk jump sequence section. The threshold value of the number of skipped nodes can be set to 2 with reference to the median value of the sample statistics. If the current number of skipped nodes is 3, the condition is met and it is determined as a jump sequence. The setting process of the abnormal start and stop section is obtained through the average time analysis of all start and stop samples. Assume that the average value of all start and stop interval samples is 25 minutes and the standard deviation is 6 minutes. Then the abnormal start and stop section is defined as the average value plus 2 times the standard deviation, that is, greater than 37 minutes is abnormal. Here, 52 minutes is significantly higher than this interval, so it meets the abnormal section condition. Finally, it is determined that this section is a jump sequence section and enters the jump sequence process section list.

[0033] S512: Call the number of jump sequence nodes and start and stop time interval data of each process section in the risk jump sequence process section list, and use the formula: ; Calculate the jump sequence level score of the process section , and integrate to obtain the jump sequence level score sequence; Among them, represents the number of jump sequence nodes of this process section, represents the maximum number of jump sequence nodes among all process sections, represents the start and stop time interval of this process section, represents the average value of the start and stop time intervals of all process sections.

[0034] First, call the number of skipped nodes and the start and stop interval time obtained from each jump sequence section in the previous sub-step, and normalize according to the maximum number of jump sequence nodes that appears in all jump sequence sections. Assume that the maximum number of jump sequence nodes in all process sections is 4. If the current process section skips 3 nodes, after normalization, it is , and then the start and stop time interval of each section Compare with the average start-stop time interval of all segments and assume minutes. If the start-stop interval of the current process segment is 52 minutes, the deviation ratio is , substitute into the formula: ; The explanations of each parameter are as follows: is the scoring result, is the number of out-of-order nodes (currently 3), , , , the calculation result of this is the scoring value of 1.39275. This value is higher than the preset out-of-order risk scoring threshold (for example, the set threshold is 1.2), then this scoring value constitutes a high-level risk score and enters the high-risk node set. The advantage of the formula is that by standardizing the number of out-of-order nodes and introducing the start-stop offset ratio to form a product score, two risk factors are effectively integrated into the same dimension, which is beneficial to identifying abnormal out-of-order process segments in the scoring system.

[0035] S513: According to the scores of each process segment in the out-of-order level scoring sequence, set the out-of-order risk scoring threshold, screen all the scoring values, retain the process segment nodes with scores higher than the scoring threshold, combine and register the process numbers, scoring values and corresponding time position information of the nodes, and connect them to the structural path of the blended traceability system to establish a polyester blended fabric process traceability node registration form; Taking the scoring value as the core basis, sort all the process segments from high to low according to the scores, and classify the process segments according to the set out-of-order risk scoring threshold. If the scoring value of a certain process segment exceeds the threshold of 1.2, it is determined as an out-of-order risk node. Taking the out-of-order level scoring sequence as the input, read the scoring value and process segment number item by item, extract the node information with all scoring values higher than 1.2. For example, the process segment with the number A102 and the score of 1.39 enters the registration scope, and at the same time extract the time period when the out-of-order occurs, such as from 13:00 to 13:45 on June 13, 2024, and construct a registration record structure including: process segment number, time interval, out-of-order level score, number of out-of-order nodes, and start-stop interval. After completion, fill in all the information into the blended process traceability registration form, and this form exists as a structural positioning information item in the subsequent process backtracking.

[0036] The above is only a preferred embodiment of the present invention, and it does not limit the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical content of the technical solution of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still belong to the protection scope of the technical solution of the present invention.

Claims

1. A polyester blended fabric production process traceability information management method, characterized in that: The following steps are involved: S1: Obtain the continuous process nodes on the polyester blended production line, capture the node index of the discontinuous node batch sequence, and establish the start-stop tension batch jump index table; S2: according to the start-stop tension batch jump index table, the jump section is set as a fixed detection window, the arrangement level spacing slope of multiple continuous points in the window is calculated, and the window of the mutation position is marked according to the multi-point slope direction to obtain the fiber level and torque mutation position set; S3: based on the fiber level and the marked mutation position time period in the torque mutation position set, counting the amplitude change frequency in each time period, selecting the interactive response area according to the change frequency, and generating the tension fluctuation synchronization section; S4: based on the recorded time segments in the tension fluctuation synchronization segment and the location of the inflection point, the density of all segments is calculated and grouped and clustered to generate a tension inflection point dense segment; S5: According to the inflection point peak section in the tension inflection point dense section, the start and stop status records of the corresponding equipment are matched, and the polyester blended fabric process traceability node registration table is established by screening the risk sections and corresponding process nodes in the start and stop status records.

2. The polyester blended fabric production process traceability information management method according to claim 1, characterized in that: The start-stop tension batch jump index table includes a jump node position index, a corresponding tension feedback index segment, a batch continuity interruption mark, and a start-stop time interval status mark. The fiber layer and torque mutation position set includes a mutation detection window position, a layer spacing slope change direction, a torque flip mark, and a mutation node identification number. The tension fluctuation synchronization section is specifically a trajectory disturbance amplitude distribution section, a tension switching frequency segment, a frequency overlap mark interval, and a synchronization response identification number. The tension inflection point dense section includes a tension peak grouping label, a section density statistic, a dense grouping index number, and a response center time interval. The polyester blended fabric process traceability node registration table includes a risk jump sequence segment position, a jump sequence level score value, a registered process node number, and a traceability level classification label.

3. The polyester blended fabric production process traceability information management method according to claim 2, characterized in that: The steps for obtaining the start-stop tension batch jump index table are specifically as follows: S111: Obtain the start and stop time sequence, material batch sequence and tension feedback timestamp sequence of continuous process nodes on the polyester blended spinning production line, arrange the start and stop time of each node according to the process sequence, calculate the intervals between the start and stop times of adjacent nodes in sequence, and determine whether the adjacent intervals are zero, so as to obtain a set of nodes with adjacent zero intervals of start and stop time; S112: according to the time period corresponding to each node in the set of adjacent zero-interval nodes of the start and stop time, the tension feedback timestamp sequence is divided and the tension feedback time segment corresponding to the start and stop time is extracted, the material batch sequence in the corresponding segment is extracted, and the material batch sequence is numbered and compared in sequence to determine whether there is a number jump in the batch sequence, and a batch jump node list in the tension time segment is obtained; S113: Call the batch jump node list in the tension time segment and the set of zero-interval nodes adjacent to the start and stop time to perform cross-judgment, filter the node indexes that have both zero start and stop time and discontinuous material batches, and generate a start and stop tension batch jump index table.

4. The polyester blended fabric production process traceability information management method according to claim 3, characterized in that: The steps for obtaining the fiber level and torque mutation position set are specifically as follows: S211: according to the time period position recorded in the start-stop tension batch jump index table, extract the fiber axial arrangement image sequence, adjacent layer spacing value sequence and torque direction symbol sequence of the corresponding drafting section and twisting section process sections and perform time synchronization processing, extract the matching structure data segment, and generate a structure sequence synchronization data set; S212: Based on the structure sequence synchronization data set, the structure sequence in the jump section is set as an equal-width fixed detection window, using the formula: ； Calculate the detection window The normalized slope change rate , using the rate of change as an indicator to construct a standard slope change trend value sequence within the window; in, Indicates The change in the segment level spacing, Indicates The time variation corresponding to the segment, Indicates the reference amplitude of the level spacing of the entire section, Indicates the base amplitude of the time difference of the entire segment, Indicates the number of spacing point pairs in the window; S213: Call each window segment in the standard slope change trend value sequence, determine whether the window segment change trend is discontinuous fluctuation, and detect whether there is a reverse flip mark in the corresponding torque direction symbol sequence, filter out the positions where both the direction inconsistency and the symbol flip exist, mark the filtered window positions, and obtain the fiber level and torque mutation position set.

5. The polyester blended fabric production process traceability information management method according to claim 4, characterized in that: The steps for obtaining the tension fluctuation synchronization section are specifically as follows: S311: Based on the marked mutation time periods in the fiber level and torque mutation position set, extract the fiber arrangement trajectory path sequence and the tension fluctuation value sequence in the corresponding time period, calculate the displacement amplitude difference per unit time in the axial direction of the trajectory path, and count the amplitude change frequency in each time segment, and perform symbol recognition on the tension fluctuation sequence, count the positive and negative value switching frequency in the same time period, and obtain a structure and tension change frequency data comparison table; S312: Call the trajectory change frequency and tension switching frequency in the structure and tension change frequency data comparison table, divide the time axis into segments and set fixed intervals, judge for each time slice whether the two types of frequencies simultaneously exceed their respective corresponding average reference values, select the overlapping segments where the fluctuation behavior appears at the same time position, summarize them in chronological order, and establish the tension fluctuation synchronization segment.

6. The polyester blended fabric production process traceability information management method according to claim 5, characterized in that: The steps for obtaining the tension inflection point dense section are specifically as follows: S411: based on the time segments in the tension fluctuation synchronization segment, extract the corresponding tension change sequence, locate all local extreme points in the sequence, divide the tension sequence into continuous segments according to the fixed time segment width, count the number of inflection points in each time segment, and generate a tension inflection point number distribution table; S412: Call the inflection point quantity value, time span, tension normalized fluctuation amplitude and extreme value change rate of each section in the tension inflection point quantity distribution table, perform time dimension normalization and unit amplitude unification processing, and use the formula: ； Calculate the current The density of turning points in each time period , get the tension inflection point density sequence; in, Indicates the number of inflection points in the current segment, Indicates the time length corresponding to the current segment. It represents the standard deviation of the unit time fluctuation of the tension sequence in the current section. Indicates the extreme value difference of tension in the current section. Indicates the previous time period The number of inflection points, Indicates the previous time period The tension extreme difference; S413: According to the density in the tension inflection point density sequence, all segments are hierarchically clustered by density, the group to which the density peak belongs is identified, and it is determined on the time axis whether they constitute a continuous segment fragment. If the density values ​​in the continuous segment are all higher than the set density judgment threshold, the corresponding segment position is recorded to obtain the tension inflection point dense segment.

7. The polyester blended fabric production process traceability information management method according to claim 6, characterized in that: The specific steps for obtaining the polyester blended fabric process traceability node registration form are as follows: S511: According to the inflection point peak section in the tension inflection point dense section, match the equipment start and stop status records, extract the start and stop records of the equipment corresponding to the section at the time points before and after the section, calculate the time interval between the previous start and stop and the next start and stop, and count the number of equipment nodes skipped in the current process section, determine whether the number of skipped nodes exceeds the skip sequence number threshold, and whether the start and stop time interval is within the preset start and stop abnormal section range, select the process sections that meet the requirements as abnormal process sections, and generate a risk skip sequence process section list; S512: Call the number of hopping nodes and start-stop time interval data of each process segment in the risk hopping process segment list, using the formula: ； Calculation process section Skip-rank rating , integration obtains the skip-order grade score sequence; in, Indicates the number of skip nodes in the target process segment. Indicates the maximum number of skip nodes in all process stages. Indicates the start and stop time interval of the target process section, It represents the average value of the start and stop time intervals of all process sections; S513: According to the score of each process section in the skipping grade scoring sequence, a skipping risk scoring threshold is set, all scoring values ​​are screened, and process section nodes with scores higher than the scoring threshold are retained. The process number, scoring value and corresponding time and position information of the node are combined and registered, and the structural path of the blended traceability system is connected to establish a polyester blended fabric process traceability node registration table.

Images