System for detecting and predicting abnormality of yarn on loom

Abstract

An object of the present invention is to provide an abnormality detection system, a system for detecting and predicting an abnormality of a raw yarn on a loom, or a system for detecting fluff of a filament yarn, which not only improves productivity and economic efficiency but also is useful as an ecology green technology.SOLUTION: Provided is an abnormality detection system capable of determining the degree of abnormality of a weft yarn based on the degree of variation in the arrival timing of the weft yarn in weft insertion of a loom, and stopping the loom when the degree of abnormality is equal to or greater than a predetermined value.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a system for detecting and predicting abnormalities in raw yarn on a loom, a system and method for detecting hairiness in filament yarn, and a system and method for weaving and processing filament yarn. [Background technology]

[0002] Filament yarns are obtained by bundling a plurality of fiber monofilaments obtained by spinning raw materials such as glass, synthetic resin, natural resin, carbon, metal, etc. Filament yarns are used to manufacture various components such as laminates, printed wiring boards, stent grafts, composite materials, reinforcing materials, and concrete crack suppression materials. Among these, glass filament yarns are known as a raw material for printed wiring boards.

[0003] For example, tens to thousands of glass fiber monofilaments measuring several μm to several tens of μm, obtained by spinning molten glass, are bundled together to form glass filament yarns, which are then temporarily wound around a drum to form what is called a cake. The glass filament yarns are then unwound from the cake and shipped in the form of glass yarns (glass threads) that have been twisted. The glass threads are woven and crossed, opened and / or sized as necessary, composited and laminated with a matrix resin such as an epoxy resin, and processed into printed wiring boards.

[0004] Glass filaments may also be shipped in the form of bobbins, which are glass yarns wound around a bobbin; glass rovings, which are made by bundling and doubling several dozen glass filament yarns; or chopped strands, which are made by cutting glass filament yarns into pieces of several millimeters to several tens of millimeters. The raw yarns from the bobbins can be used as warp and / or weft yarns in a weaving process. Glass rovings are used as raw materials for glass fiber reinforced plastics (FRP, FRTP), and chopped strands are used as reinforcing materials for thermoplastic resins.

[0005] In the process of bundling multiple fiber monofilaments into a filament yarn, the process of unwinding the filament yarn from the cake, the weaving process, or the processing process, the fiber monofilaments come into contact with each other and rub against each other, which can cause fluff defects in which the glass fiber monofilaments are partially broken or woven in the broken state. Fluff defects not only deteriorate workability but can also affect the quality of the final product. Conventionally, methods for controlling looms have been studied from the perspective of preventing weft insertion errors due to yarn breakage in the weaving process (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Publication No. 2019-196556 Summary of the Invention [Problem to be solved by the invention]

[0007] For example, as described in Patent Document 1, a technique is known for detecting the arrival time of a weft yarn blown by an air jet.

[0008] However, conventional looms and their control methods leave room for improvement in terms of productivity, economy, ecology and / or green technology.

[0009] Therefore, an object of the present invention is to provide an abnormality detection system, a raw yarn abnormality detection and prediction system on a loom, or a filament yarn hairiness detection system that not only improves productivity and economic efficiency but is also useful as an ecological and green technology. [Means for solving the problem]

[0010] As a result of extensive research, the present inventors have found that the above-mentioned problems can be solved by detecting situations in which low-quality intermediates or products are produced in a manufacturing process and enabling the operation of a manufacturing apparatus to be stopped as necessary, and have completed the present invention. <1> An abnormality detection system that determines the degree of abnormality of a weft thread based on the degree of variation in the timing of the weft thread arrival during weft insertion on a loom, and can stop the loom if the degree of abnormality is equal to or greater than a predetermined value. <2> Item 1. An anomaly detection system according to item 1, wherein, when the degree of anomaly is equal to or greater than a predetermined value, the result of the determination of the degree of anomaly is displayed by at least one selected from the group consisting of screen display, printing, sensory stimulation, and data transmission. <3> 1. A filament yarn hairiness detection system, comprising: A fuzz detection system comprising: an abnormality degree calculation means for calculating the abnormality degree of a weft yarn from the degree of variation in the timing of the weft yarn arrival during weft insertion in a loom, using a calculation formula stored in an abnormality degree calculation formula storage means; and a loom abnormality stop means for sending an operation stop signal to the loom when the abnormality degree is equal to or greater than a predetermined value. <4> Item 4. The fluff detection system according to item 3, further comprising a loom abnormality warning means for raising an alarm when the degree of abnormality is equal to or greater than a predetermined value. <5> 5. The fluff detection system according to item 3 or 4, wherein the calculation formula includes a function or a correspondence table for calculating the degree of abnormality of the weft yarn based on a sequence of measured values ​​of the sensor during the weft insertion. <6> 6. The fluff detection system according to any one of items 3 to 5, further comprising: a feature conversion means for converting the degree of variation into a feature using a conversion formula stored in a feature conversion formula storage means. <7> 7. The fluff detection system according to item 6, wherein the conversion formula includes a function or a correspondence table that converts a sequence of measurement values ​​of the sensor in the weft insertion into a feature quantity. <8> 8. The fluff detection system according to item 6 or 7, wherein the feature is the average, variance, or distribution of the arrival times. <9> 9. The fluff detection system according to any one of items 3 to 8, further comprising a weft abnormality determination means for determining whether the weft is abnormal or not using a determination formula stored in a weft abnormality determination formula storage means. <10> Item 10. The fluff detection system according to item 9, wherein the judgment formula includes a function or a pass / fail map for determining whether the weft yarn satisfies a quality standard during weaving based on the abnormality degree or its transition. <11> 11. The fluff detection system according to any one of items 3 to 10, further comprising a loom installation environment information collecting means for collecting ambient environment information about a location where the loom is installed. <12> Item 12. The fluff detection system according to item 11, wherein the ambient environment information is at least one selected from the group consisting of temperature, humidity, and wind direction. <13> 13. The fluff detection system according to any one of items 3 to 12, further comprising a weft advance physical property information storage means for storing the physical property information before the weft insertion for a part of the weft. <14> 14. The fluff detection system according to any one of items 3 to 13, further comprising a loom characteristic information storage means for storing characteristic information of the loom. <15> Item 15. The fuzz detection system according to item 14, wherein the characteristic information of the loom is at least one selected from the group consisting of the model of the loom, the number of maintenances, the most recent maintenance date and time, the maintenance means, and the model of the reed included in the loom. <16> The fluff detection system according to any one of items 6 to 8, further comprising an abnormality degree calculation formula advance changing means that accumulates the feature amounts and batch-changes the calculation formula stored in the abnormality degree calculation formula storage means so that a predetermined evaluation standard is satisfied based on the accumulated feature amounts. <17> The fluff detection system according to any one of items 6 to 8, further comprising an abnormality degree calculation formula sequential change means that accumulates the feature amounts, sequentially learns normal states and abnormal states based on the accumulated feature amounts, and sequentially changes the calculation formula stored in the abnormality degree calculation formula storage means based on the normal states and the abnormal states. <18> Item 18. The fluff detection system according to item 17, wherein the means for successively changing the abnormality degree calculation formula successively changes a parameter or a threshold value in the calculation formula. <19> 19. The fluff detection system according to any one of items 6 to 8 and 16 to 18, further comprising a weft change detection means for detecting a change in the row of the feature values ​​and / or a stop time of the loom to thereby detect a change in the weft, and adjusting a conversion formula for the feature values ​​and / or a calculation formula for the degree of abnormality. <20> 20. The fluff detection system according to any one of items 3 to 19, which is used offline. <21> 20. The fluff detection system according to any one of items 3 to 19, which is used inline. [Effects of the Invention]

[0011] According to the present invention, an abnormality detection system, a raw yarn abnormality detection and prediction system on a loom, and a filament yarn hairiness detection system are provided, which can detect situations in which low-quality intermediates or products are being continuously produced and stop the manufacturing equipment as necessary, thereby not only improving productivity and economic efficiency but also being environmentally friendly as an ecological and green technology. [Brief explanation of the drawings]

[0012] [Figure 1] 1A and 1B are schematic diagrams for explaining the configuration of a fluff detection system according to one embodiment of the present invention, showing a schematic diagram of a loom (a) and a schematic diagram of a fluff detection system (b). [Figure 2] 1 is a flowchart of a fluff detection method according to an embodiment of the present invention. [Figure 3]1 is a schematic diagram illustrating the configuration of a fluff detection system according to a preferred embodiment of the present invention. [Figure 4] 1 is a flowchart illustrating an example of a predictive detection algorithm. [Figure 5] 1 is a schematic diagram illustrating an overall process flow including a fluff detection system according to one embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0013] Below, a form for implementing the present invention (hereinafter referred to as an "embodiment") will be described in detail with reference to the drawings. However, the present invention is not limited to the embodiment or drawings described below, and various modifications are possible within the scope that does not deviate from the gist of the present invention.

[0014] First Embodiment In the first embodiment, an abnormality detection system is provided that determines the degree of abnormality of a weft yarn based on the degree of variation in the timing of weft yarn arrival during weft insertion on a loom, and can stop the loom if the degree of abnormality is equal to or greater than a predetermined value. The abnormality detection system according to the first embodiment detects an abnormal situation in which low-quality intermediate products or finished products are being produced, and stops the loom as necessary, thereby improving productivity and economy, and is also useful as an eco-green technology.

[0015] The anomaly detection system according to the first embodiment can be used as an apparatus or method for detecting anomalies in the field of weft insertion using a loom using warp and weft yarns. For example, weft insertion is performed in a weaving process, a filament yarn weaving process, etc. When glass filament yarns are used, the anomaly detection system according to the first embodiment is preferably used in the manufacture of glass cloth and the manufacture of raw materials for printed wiring boards.

[0016] The timing of the weft arrival can be measured, for example, as pressure, pressure angle, or laser light blocking by a device that positions the weft relative to the warp threads placed on the reed, and a device that detects the start and end of weft insertion. The degree of variation in the timing of arrival of multiple weft threads and the degree of abnormality based thereon can be determined by a calculation component including an arithmetic processing unit and / or a storage medium. The calculation component and / or storage medium may be equipped with a display unit such as a monitor, or a transmission device such as a modem.

[0017] One or more predetermined values ​​of the degree of abnormality can be determined in advance due to, for example, a defect in the raw yarn, a fluff defect in the weft yarn, a defect in the weft bobbin, a defect in the loom, etc., and can be stored in a storage medium. The stopping means of the loom may be a component that physically stops the loom, a component that sends a stop signal to the loom, a component that emits a stop signal to the loom, or a combination thereof, and can be in contact with the loom or positioned away from the loom.

[0018] The anomaly detection system according to the first embodiment preferably displays the result of the abnormality assessment and issues an alarm when the degree of abnormality described above is equal to or greater than a predetermined value, and more preferably displays the result of the abnormality assessment by at least one selected from the group consisting of screen display, printing, sensory stimulation, and data transmission. The screen display and data transmission can be performed simultaneously or separately by the display unit and transmitter described above. Printing is performed by printing the result of the assessment on a print medium using a printer. The sensory stimulation may be any stimulation that stimulates human senses and issues an alarm, such as sound, light emission, fragrance, sound change, color change, deformation, or temperature change.

[0019] The anomaly detection system according to the first embodiment can be used, for example, offline or inline.

[0020] Second Embodiment In a second embodiment, there is provided a filament yarn hairiness detection system, comprising: an abnormality degree calculation means for calculating the degree of abnormality of a weft yarn from the degree of variation in the arrival timing of the weft yarn during weft insertion of the loom, using a calculation formula stored in an abnormality degree calculation formula storage means; a loom abnormality stopping means for sending an operation stop signal to the loom when the calculated abnormality level is equal to or greater than a predetermined value; A fuzz detection system is provided comprising:

[0021] The fuzz detection system of the second embodiment is equipped with an abnormality degree calculation means and a loom abnormality stopping means, and is therefore able to detect situations in which filament yarn or glass cloth with fuzz defects continues to be produced, and stop the operation of the loom as necessary, thereby improving productivity and economy, and is also useful as an eco-green technology.

[0022] In the second embodiment, after converting the measured values ​​into feature quantities, the feature quantities are compared with those of past normal and abnormal behaviors to calculate the degree of abnormality, which can be displayed numerically or graphically. Therefore, compared to a case where the measured values ​​are not collected or displayed, it is possible to know abnormalities in the weft yarn one after another, and if the degree of abnormality is high, it is possible to minimize the production of low-quality fabrics by stopping the loom.

[0023] The filament yarn hairiness detection system according to the second embodiment can be used, for example, offline or inline.

[0024] Third Embodiment In a third embodiment, a fuzz detection system for filament yarn is provided that combines the configurations of the first and second embodiments.

[0025] Configurations common to the first, second, and third embodiments, or other configurations, and preferred embodiments will be described below.

[0026] 〔composition〕 Fig. 1(a) shows a schematic diagram of a loom 200(a) and a fuzz detection system 100(b). Referring to Fig. 1(a), the loom 200 includes a bobbin 210, a metal fiber detector 220, an FDP 240 with pins 230, a reed 250, a main nozzle 270 with an electropneumatic regulator 260, a sub-nozzle 280, a cutter 290, and a feeler 300. Weft insertion can be performed by unwinding a weft from the weft bobbin 210 and advancing the weft from the main nozzle 270 against the warp placed on the reed 250 using, for example, an air jet. Weft insertion can be performed at any loom angle, for example, between 90° and 240°.

[0027] The main nozzle 270 and the sub-nozzle 280 are provided as nozzles for weft insertion. The main nozzle 270 is disposed upstream in the weft transport direction, while the sub-nozzle 280 is disposed downstream in the weft transport direction from the main nozzle 270. A single main nozzle 270 is provided, while a plurality of sub-nozzles 280 are provided.

[0028] The main nozzle 270 injects air when a main valve (not shown) is open, and stops injecting air when the main valve is closed. The main nozzle 270 or the main valve can be physically, electrically, or data-communicatively connected to a loom abnormality stop means of the detection system.

[0029] An electro-pneumatic regulator 260 can be connected to the main nozzle 270 to adjust the pressure of compressed air generated by an air compressor (not shown). The compressed air is supplied to the main nozzle 270 via a main valve (not shown) and used to blow off the weft yarn. The electro-pneumatic regulator 260 can be physically, electrically, or data-communicatively connected to a loom abnormality stop means of the detection system.

[0030] The sub-nozzles 280 spray or stop spraying air depending on the open / close state of their corresponding sub-valves (not shown). The sub-nozzles 280 may be arranged along the longitudinal direction of the reed 250 as shown in Fig. 1, and / or the direction of the sub-nozzles may be set to form an angle of approximately 45° with respect to the spray direction of the main nozzle 270. Similar to the main nozzle 270, the sub-nozzles 280 may be connected to a valve, an air compressor, a regulator, a loom abnormality stop means of a detection system, etc.

[0031] The feeler 300 detects whether the weft has reached a predetermined position when the weft is inserted by spraying air from the main nozzle 270 and the sub-nozzle 280, and is sometimes called an arrival sensor (13). The predetermined position can be set on the weft insertion end side, farther from the main nozzle 270 in the longitudinal direction of the reed 250, in accordance with the weaving width of the fabric.

[0032] The feeler 300 is configured by, for example, an optical sensor. The feeler 300 can output a detection signal when the tip of the weft yarn, which is transported in the longitudinal direction of the reed 250 by air injection from the weft insertion nozzle, reaches a predetermined position. Therefore, the weft arrival timing at which the weft yarn reaches the predetermined position may be the timing at which the feeler 300 outputs the detection signal.

[0033] Referring to FIG. 1(b), the abnormality or fluff detection system 100 includes an input device 1 equipped with a main nozzle sensor 11, a sub-nozzle sensor 12, and an arrival sensor 13, etc., a data processing device 2 that operates under program control, a memory device 3 that stores information, and an output device 4 such as a display device, a mobile terminal device, or a printing device.

[0034] In the input device 1, the main nozzle sensor 11, the sub-nozzle sensor 12, and the reach sensor 13 can be physically, electrically, or data-communicatively connected to the main nozzle 270, the sub-nozzle 280, and the feeler 300, respectively. In addition, the feeler 300 itself may be the reach sensor 13.

[0035] The main nozzle sensor 11 detects, for example, the timing of starting the air jet for the weft, the number of weft insertions, the weft insertion pressure, the type of weft, the number of wefts, etc., and outputs the signals. In particular, it is preferable that the main nozzle sensor 11 detects and outputs the pressure, the number of wefts, or the number of weft insertions.

[0036] The sub-nozzle sensor 12 detects, for example, the number of weft insertions, weft insertion pressure, the number of weft insertion direction adjustments, the type of weft yarn, the number of weft yarns, the main nozzle state, etc., and outputs the detected signals. Of these, it is preferable that the sub-nozzle sensor 12 detects and outputs pressure.

[0037] The arrival sensor 13 detects the weft arrival timing when the weft reaches a predetermined position, the number of weft insertions, the weft insertion pressure, the type of weft, the number of wefts, etc., and outputs the signals. In particular, it is preferable that the arrival sensor 13 detects and outputs the weft arrival timing using an optical sensor. Note that the weft insertion timing can be understood as the arrival angle.

[0038] The storage device 3 includes a feature quantity conversion formula storage unit 31, an abnormality degree calculation formula storage unit 32, and a weft abnormality determination formula storage unit 33.

[0039] The feature conversion formula storage unit 31 stores in advance conversion formulas such as functions or correspondence tables for converting the measurement value sequence of each sensor into feature values ​​used to calculate the degree of anomaly. Examples of functions include basic statistics such as the mean, variance, or distribution.

[0040] The abnormality degree calculation formula storage unit 32 stores in advance a calculation formula such as a function or a correspondence table prepared in advance to be used for calculating the abnormality degree of the weft yarn based on each feature amount. Examples of the function include a regression formula or a decision tree based on an if-then rule.

[0041] The weft abnormality judgment formula storage unit 33 stores in advance judgment formulas such as functions, pass / fail maps, or correspondence tables used to judge whether the weft yarn being woven satisfies the quality standard based on the abnormality degree or its transition. An example of a function is a sequential test that judges it to be abnormal only when the state where the abnormality degree is equal to or greater than a threshold exceeds a certain range.

[0042] The data processing device 2 includes a feature conversion means 21, an abnormality degree calculation means 22, and a weft abnormality determination means 23.

[0043] The feature conversion means 21 converts the measurement value sequence provided by the input device 1 into a feature using a conversion formula stored in the feature conversion formula storage unit 31 as an input of a function or a correspondence table. The feature may be the mean, variance, or distribution of the arrival timings described above.

[0044] The abnormality degree calculation means 22 receives the feature of the measurement value converted by the feature conversion means 21 as an input and calculates the degree of abnormality using the calculation formula stored in the abnormality degree calculation formula storage unit 32 .

[0045] The weft abnormality determination means 23 receives the degree of abnormality of the measured value calculated by the abnormality degree calculation means 22 as an input and determines whether the weft is abnormal or not using a determination formula stored in the weft abnormality determination storage unit 33.

[0046] [Operation] The operation of the detection system according to the first, second or third embodiment will be described in detail with reference to Figures 1 and 2. Figure 2 shows a flowchart of the fluff detection method.

[0047] The measurement value sequence given from the input device 1 is supplied to the feature conversion means 21 (step A1).

[0048] The feature conversion means 21 inputs this measurement sequence into a conversion formula stored in the feature conversion formula storage unit 31. This conversion formula outputs the mean, variance, distribution, etc. of the measurement values ​​as feature quantities, and provides these feature quantities to the anomaly degree calculation means 22. At the same time, the transition of the feature quantities is output to the output device 4 as numerical values ​​or graphs (step A2).

[0049] Next, the abnormality degree calculation means 22 receives the feature quantities such as the mean, variance, and distribution of the measured values ​​converted by the feature quantity conversion means 21, and calculates the degree of abnormality using the calculation formula stored in the abnormality degree calculation formula storage unit 32. This calculation formula calculates a high degree of abnormality when there is a high probability of an abnormality, based on the feature quantities of past normal and abnormal behaviors. This abnormality degree is provided to the weft abnormality determination means 23, and at the same time, the transition of the abnormality degree is output to the output device 4 as a numerical value or a graph (step A3).

[0050] Next, the weft abnormality determination means 23 receives the degree of abnormality of the measured value calculated by the abnormality degree calculation means 22, and determines whether or not the weft is abnormal using a determination formula stored in the weft abnormality determination storage unit 33. This determination formula determines that an abnormality has occurred when there is a high probability of an abnormality, such as when the abnormality degree sequence shows a high index continuously over a certain period of time, and simultaneously outputs the transition of the abnormality determination results to the output device 4 as numerical values ​​or a graph (step A4).

[0051] Preferred Embodiments 3 is a schematic diagram showing the configuration of a detection system according to a preferred embodiment of the present invention. In addition to the components described above, the abnormality or fuzz detection system 100 according to the preferred embodiment includes at least one selected from the group consisting of a loom installation environment sensor 14, a weft yarn advance physical property information storage unit 34, a loom characteristic information storage unit 35, an abnormality degree calculation formula advance changing means 24, an abnormality degree calculation formula sequential changing means 25, a weft yarn change detection means 5, a loom abnormality warning device 41, and a loom abnormality stop device 42.

[0052] The loom installation environment sensor 14 collects data on the ambient environmental conditions or information such as temperature, humidity, wind direction, etc., where the loom is installed. By using this data, the influence of the environment where the loom is installed can be reflected, and if the environment changes, the influence can be factored into the calculation of the abnormality level.

[0053] The weft yarn prior physical property information storage unit 34 stores physical property information such as the results of detailed prior inspection of the state of a portion of the weft yarn using an inspection machine. Examples of the inspection results include the number of weft yarn breaks and slacks, and by incorporating this prior information as feature quantities, it becomes possible to calculate the degree of abnormality with higher accuracy.

[0054] The loom characteristic information storage unit 35 stores characteristic information of each loom, such as the manufacturer and model of the loom, the means and number of maintenances, the date and time of the most recent maintenance, the type and model of the reed included in the loom, etc. By adjusting the parameters or thresholds based on this information when calculating the abnormality level, it becomes possible to calculate the abnormality level more accurately for each loom.

[0055] The abnormality degree calculation formula advance changing means 24 accumulates feature quantities collected and converted over a certain period in the past, and changes the calculation formula in the abnormality degree calculation formula storage unit 32 based on the feature quantities so that a certain or predetermined evaluation criterion is met. This change of the calculation formula is preferably performed batch by batch. The evaluation criterion may include not only the degree of abnormality but also a more detailed classification of the type of abnormality to be output.

[0056] The means for successively changing the abnormality degree calculation formula 25 accumulates feature amounts collected and converted over a certain period in the past, and successively learns normal and abnormal states based on the feature amounts, and accordingly successively changes the parameters or thresholds of the calculation formula in the abnormality degree calculation formula storage unit 32. This makes it possible to calculate the degree of abnormality based on evaluation criteria that follow gradual changes in the surrounding environment, loom, and weft.

[0057] The weft change detection means 5 detects the change of the weft yarn by detecting a change in the feature sequence and / or the stop time of the loom, and adjusts the conversion formula for the feature quantity and / or the calculation formula for the abnormality degree. By using the calculation results, it is possible to automatically determine that the weft yarn has been changed, and it becomes easy to extract the information on the corresponding weft yarn from the weft advance physical property information storage unit.

[0058] The loom abnormality alarm device 41 integrates the results collected by the output device 4, and if it determines that the weft is abnormal, it issues an alarm to the loom operator, requesting him to decide whether or not to continue operating the loom.

[0059] The loom abnormality stop device 42 integrates the results collected by the output device 4, and if it determines that the weft yarn is abnormal, it sends a stop signal to the loom to forcibly stop the operation of the loom.

[0060] [Predictive detection algorithm] FIG. 4 illustrates a flowchart of a predictive detection algorithm. Assuming that arrival timing equals arrival angle, the predictive detection algorithm collects loom data, such as the weft arrival angle, converts the weft arrival angle into statistical quantities, and then predicts and detects the number of fluff particles (n1, n2, n3, n4, n5, n6, n7, etc.) based on the standard deviation, skewness, and kurtosis of the arrival angle. While a regression tree is exemplified as a predictive detection algorithm, it is not limited to this. For example, regression methods, classification methods, neural networks, SVMs, random forests, etc., as described in "Foundations of Statistical Learning: Data Mining, Inference, and Prediction" by Trevor Hastie, Robert Tibshirani, and Jerome Friedman (Kyoritsu Shuppan) may be used. The predictive detection algorithm may have a single layer or multiple layers, and may include combinations, permutations, or rearrangements of the standard deviation, skewness, and kurtosis of the arrival angle.

[0061] The predictive detection algorithm shown in FIG. 4 is incorporated into the hairiness detection system, preferably into at least one of the abnormality degree calculation means, the loom abnormality stopping means, the abnormality degree calculation formula advance changing means 24, the abnormality degree calculation formula successive changing means 25, and the weft yarn change detection means 5, so as to prevent the loom from continuing to produce low-quality or poor-quality cloth.

[0062] [Method for detecting fluff in filament yarn] The method for detecting hairiness of a filament yarn of the present invention is carried out using a hairiness detection device equipped with the abnormality degree calculation means and the loom abnormality stop means described above. More specifically, the method for detecting hairiness of a filament yarn includes the following steps: an abnormality degree calculation step of calculating the degree of abnormality of the weft yarn from the degree of variation in the arrival timing of the weft yarn during weft insertion of the loom, using a calculation formula stored in an abnormality degree calculation formula storage means; If the abnormality level is equal to or greater than a predetermined value, a loom abnormality stopping process is performed in which a signal to stop operation is sent to the loom. Execute.

[0063] The method for detecting hairiness of a filament yarn can be carried out, for example, according to the flowchart shown in FIG.

[0064] [Overall process flow of weaving] 5 is a schematic diagram of an overall weaving process flow including the above-described fuzz detection system. Arranged from upstream to downstream in the process flow are a (yarn) surface layer inspection machine 400, a sensing-enabled loom 201, and a fuzz inspection machine 500, and the abnormality or fuzz detection system according to the present invention can be incorporated into the inspection step of the process flow.

[0065] Alternatively, the storage device 3, data processing device 2, output device 4, etc. of the anomaly or fuzz detection system may reside in a location isolated from the system, in data communication with it, or on the cloud.

[0066] The overall process flow is broadly divided into an application platform 6 and an analysis platform 7, and both platforms are overlapped or connected by a data server 678.

[0067] The application board 6 automates data collection and processing to improve data accuracy and reduce the workload of the operator. The application board 6 transmits and receives data (ii) such as yarn diameter and yarn defects between the data server 678 and the surface layer inspection machine 400, transmits and receives data (iii) such as waveform data and weft data during weaving or weft insertion, and fuzz detection data (iv) between the data server 678 and the sensing-enabled loom 201, displays the transmitted and received data on the display device 9 as desired, and transmits and receives fuzz inspection data (v) between the data server 678 and the fuzz inspection machine 500.

[0068] The surface layer inspection machine 400 inspects the surface layer of the yarn or bobbin using, for example, the MT method, and collects and transmits data (ii) such as yarn diameter and yarn defects to the data server 679. On the other hand, it receives a signal from the application base 6 regarding the pass / fail of the yarn and can decide whether to continue or change the yarn used.

[0069] The sensing-enabled loom 201 is equipped with, for example, a pressure sensor, an arrival (flying) sensor, etc., and uses these to collect and collect data (iii) such as waveform data and weft data during weaving or weft insertion, and transmit it to the data server 679. On the other hand, the sensing-enabled loom 201 receives fluff detection data (iv) that has been pre-processed based on a prediction model stored in the data server and subsequently subjected to inference processing, and can then decide whether to operate or stop the loom.

[0070] The fluff inspection machine 500 actually measures the presence or absence or details of fluff in the obtained fabric or cloth and transmits fluff inspection data (v) to the data server, and on the other hand, receives a signal regarding the pass / fail of the fabric or cloth from the application base 6, and can further transmit information to an operator or the surrounding environment, for example, via an enhanced voice service (EVS).

[0071] The analysis platform 7 speeds up the analysis cycle, improves detection performance, and adapts to changes in the condition or environment of the inspection machine or loom. The analysis board is equipped with analysis means 10 including a computer, an arithmetic processing device, a storage medium, etc., and receives and analyzes various data (ii to v) from the data server 678, constructs a prediction model (i), and transmits it to the data server 678. The analysis platform 7 can contribute to speeding up the analysis cycle and improving detection performance by transmitting and receiving data between the data server 678 and the analysis means, and by performing associated machine learning and deep learning.

[0072] The detection process described above makes it possible to change yarns that may be defective before they are used, to detect situations where low-quality intermediate products or products are being produced and stop the loom, and to instantly determine whether the resulting woven fabric or cloth is acceptable or not, thereby improving productivity and economy and being environmentally friendly in terms of resources. [Explanation of symbols]

[0073] 100 Detection System 1. Input Device 11 Main nozzle sensor 12 Sub-nozzle sensor 13 Reach Sensor 14 Loom installation environment sensor 2. Data Processing Device 21 Feature transformation means 22 Abnormality degree calculation means 23 Weft abnormality determination means 24. Pre-changing method for calculating abnormality degree 25. Sequential change method for calculating abnormality degree 3 Storage device 31 Feature transformation formula memory unit 32 Abnormality degree calculation formula storage unit 33 Weft abnormality judgment formula memory section 34 Weft yarn advance physical property information storage unit 35 Loom characteristic information storage unit 4 Output Devices 41 Loom abnormality alarm device 42 Loom abnormal stop device 5. Weft change detection means

Claims

1. An abnormality detection system that determines the degree of abnormality of a weft thread based on the degree of variation in the timing of the weft thread arrival during weft insertion on a loom, and can stop the loom if the degree of abnormality is equal to or greater than a predetermined value.

2. The anomaly detection system according to claim 1 , wherein when the degree of abnormality is equal to or greater than a predetermined value, the determination result of the degree of abnormality is displayed by at least one selected from the group consisting of screen display, printing, sensory stimulation, and data transmission.

3. 1. A filament yarn hairiness detection system, comprising: A fuzz detection system comprising: an abnormality degree calculation means for calculating the abnormality degree of a weft yarn from the degree of variation in the timing of the weft yarn arrival during weft insertion in a loom, using a calculation formula stored in an abnormality degree calculation formula storage means; and a loom abnormality stop means for sending an operation stop signal to the loom when the abnormality degree is equal to or greater than a predetermined value.

4. 4. The fluff detection system according to claim 3, further comprising a loom abnormality warning means for raising an alarm when the degree of abnormality is equal to or greater than a predetermined value.

5. The fluff detection system according to claim 3 or 4, wherein the calculation formula includes a function or a correspondence table for calculating the degree of abnormality of the weft yarn based on a sequence of measured values ​​of the sensor during the weft insertion.

6. The fluff detection system according to any one of claims 3 to 5, further comprising: a feature conversion means for converting the degree of variation into a feature using a conversion formula stored in a feature conversion formula storage means.

7. The fluff detection system according to claim 6 , wherein the conversion formula includes a function or a correspondence table for converting a sequence of measurement values ​​of a sensor into feature quantities during the weft insertion.

8. The fluff detection system according to claim 6 or 7, wherein the feature amount is an average, variance, or distribution of the arrival times.

9. The fluff detection system according to any one of claims 3 to 8, further comprising a weft abnormality determination means for determining whether the weft is abnormal or not using a determination formula stored in a weft abnormality determination formula storage means.

10. The fuzz detection system according to claim 9 , wherein the judgment formula includes a function or a pass / fail map for determining whether the weft yarn satisfies a quality standard during weaving based on the degree of abnormality or its transition.

11. The fluff detection system according to any one of claims 3 to 10, further comprising a loom installation environment information collecting means for collecting ambient environment information of a location where the loom is installed.

12. The fluff detection system according to claim 11 , wherein the ambient environment information is at least one selected from the group consisting of temperature, humidity, and wind direction.

13. The fluff detection system according to any one of claims 3 to 12, further comprising a weft advance physical property information storage means for storing physical property information before the weft insertion for a portion of the weft.

14. The fluff detection system according to any one of claims 3 to 13, further comprising a loom characteristic information storage means for storing characteristic information of the loom.

15. The fluff detection system according to claim 14, wherein the characteristic information of the loom is at least one selected from the group consisting of the model of the loom, the number of maintenances, the most recent maintenance date and time, the maintenance means, and the model of the reed included in the loom.

16. The fluff detection system according to any one of claims 6 to 8, further comprising an abnormality degree calculation formula advance changing means for storing the feature amounts and batch changing the calculation formula stored in the abnormality degree calculation formula storage means so as to satisfy predetermined evaluation criteria based on the stored feature amounts.

17. The fluff detection system according to any one of claims 6 to 8, further comprising an abnormality degree calculation formula sequential change means for accumulating the feature amounts, sequentially learning normal and abnormal states based on the accumulated feature amounts, and sequentially changing the calculation formula stored in the abnormality degree calculation formula storage means based on the normal and abnormal states.

18. The fluff detection system according to claim 17 , wherein the means for successively changing the abnormality degree calculation formula successively changes a parameter or a threshold value in the calculation formula.

19. The fluff detection system according to any one of claims 6 to 8 and 16 to 18, further comprising a weft change detection means for detecting a change in the row of the feature quantities and / or a stop time of the loom to thereby detect a change in the weft yarn, and adjusting a conversion formula for the feature quantities and / or a calculation formula for the degree of abnormality.

20. The fluff detection system according to any one of claims 3 to 19, which is used offline.

21. The fluff detection system according to any one of claims 3 to 19, which is used in-line.

Images