Intelligent evaluation system for tensile property of down jacket fabric based on big data analysis

Abstract

The invention discloses an intelligent evaluation system for the tensile property of a down jacket fabric based on big data analysis, relates to the technical field of down jacket fabric tensile testing, and solves the problems that an original detection mode is too high in subjectivity and low in precision. According to the invention, deep detection is carried out on an abnormal area from different angles through the front analysis end and the back analysis end; the front analysis end accurately analyzes the spacing parameters of the hole sites between the two groups of circles by constructing an abnormal center circle and an outer circle, and can accurately judge whether the front test of an abnormal area is normal or not; and the reverse analysis end generates a diffusion interval and performs scale error confirmation by confirming the diffusion degree of the silk threads wound in the hole sites in the reverse area, so that the reverse test condition of the abnormal area is comprehensively evaluated, and the comprehensive and three-dimensional evaluation of the tensile property of the down jacket fabric is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of down jacket fabric tensile testing, and in particular to an intelligent evaluation system for tensile performance of down jacket fabric based on big data analysis. Background Art

[0002] In the process of continuous development of the down jacket industry, the tensile performance of fabrics, as a key quality indicator, has received more and more attention. As consumers' requirements for the quality of down jackets are increasing, they not only expect them to have good warmth retention performance, but also put forward higher standards for wearing comfort and durability. The tensile performance of fabrics directly affects the performance of down jackets in daily wear and exercise, such as whether they are easy to move and whether they will be damaged due to stretching.

[0003] Traditional tensile testing methods for down jacket fabrics have many limitations. In the early days, they mostly relied on manual observation and simple measurement. The testers observed the appearance changes of the fabric during the stretching process with their naked eyes and used simple measuring tools to measure the dimensions before and after stretching. This method is highly subjective, and the judgment standards of different testers vary, which makes it difficult to ensure the accuracy of the test results. Moreover, manual testing is inefficient and it is difficult to meet the needs of rapid and large-scale testing in large-scale production. At the same time, traditional methods are difficult to comprehensively and deeply analyze the subtle differences in the tensile properties of fabrics. There is a lack of effective detection methods for the relationship between the structural changes of the internal silk threads such as splicing and winding and the tensile properties of the fabrics, and it is impossible to accurately locate abnormal situations and their causes. This has restricted the improvement of the quality of down jacket fabrics and the optimization of production processes to a certain extent.

[0004] With the advancement of science and technology, big data analysis technology has gradually emerged and has been widely used in various fields. In the textile industry, the use of big data analysis to intelligently evaluate the tensile properties of down jacket fabrics has become a new development direction. By introducing high-definition image acquisition equipment, more accurate and detailed fabric surface image information can be obtained, providing a rich data basis for subsequent in-depth analysis. In this context, the development of an intelligent evaluation system for the tensile properties of down jacket fabrics based on big data analysis has important practical significance. It aims to overcome the drawbacks of traditional testing methods and achieve accurate, comprehensive and efficient testing of the tensile properties of down jacket fabrics, thereby promoting the high-quality development of the entire down jacket industry. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides an intelligent evaluation system for the tensile properties of down jacket fabrics based on big data analysis, which solves the problem that the original detection method is too subjective and has low accuracy.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent evaluation system for tensile properties of down jacket fabrics based on big data analysis, comprising:

[0007] The high-definition image acquisition terminal acquires high-definition images of the surface of the down jacket fabric involved in the tensile performance test and transmits them to the testing center;

[0008] The testing center performs fabric tension detection on high-definition images and confirms abnormal signal display based on the detection results. The testing center includes a different area confirmation unit, a storage unit, a front analysis end, and a back analysis end:

[0009] The out-of-area confirmation unit compares the acquired high-definition image with the complete image preset in the storage unit, confirms the abnormal part of the comparison and performs specific calibration of the abnormal area. The specific method is as follows:

[0010] Identify the spacing between a number of streaks from the acquired high-definition image, and compare the confirmed spacing with the complete image preset in the storage unit to identify whether the spacing at the streaks at the same position is consistent. If the comparison results are consistent, no processing is required. If the comparison results are inconsistent, the abnormal comparison point is marked as an abnormal area;

[0011] The front analysis end re-analyzes the high-definition image associated with the abnormal area to identify whether the front test of the abnormal area is normal. The specific execution ends are the analysis graph construction unit and the spacing parameter analysis unit. The analysis graph construction unit receives the high-definition image marked with the abnormal area, analyzes the marked high-definition image, intercepts the analysis graph from the high-definition image, and transmits the intercepted analysis graph to the spacing parameter analysis unit. The specific method is as follows:

[0012] Confirm the marked abnormal area from the high-definition image, confirm the maximum value of the distance between several points on the edge of the abnormal area, and use this maximum value as the diameter to construct a set of abnormal center circles;

[0013] Then radiate the abnormal center circle around it, with the radiation parameter being X1 cm, where X1 is a preset value, to obtain a set of outer circles;

[0014] According to the confirmed abnormal center circle and outer circle, the high-definition image is directly intercepted, the regional graphics belonging to the outer circle are directly intercepted and marked as analysis graphics, and the analysis graphics are transmitted to the spacing parameter analysis unit;

[0015] The spacing parameter analysis unit analyzes the abnormal center circle and outer circle in the analysis graph to determine the spacing parameters of the holes between the two groups of circles. Based on the specific comparison results, it is confirmed whether the positive test of the abnormal area is normal. The specific method is as follows:

[0016] Confirm the several micropores in the abnormal center circle, confirm the distance parameters between the diagonal points in the micropores, and mark the confirmed distance parameters as Ji , where i represents different micropores within the abnormal center circle;

[0017] Then confirm several micropores in the outer circle of the high-definition image, confirm the distance parameters between the diagonal points in the micropores, and mark the confirmed distance parameters as J k , where k represents the different micropores in the outer circle;

[0018] The two different sets of distance parameters are processed by averaging to obtain the mean JJ belonging to Ji i , get the value belonging to J k The mean value of JJ k , when JJ i >JJ k ×1.3, the positive test abnormal signal is generated by the detection signal generation unit. i ≤JJ k ×1.3, a positive test normal signal is generated by the detection signal generation unit;

[0019] The reverse side analysis end, based on the high-definition image associated with the abnormal area, locks the reverse side area of ​​the back, and based on the regional image of the reverse side area, identifies whether the reverse side test of the abnormal area is normal. The specific execution ends are the reverse side point confirmation unit, the diffusion parameter analysis unit and the standard deviation confirmation unit;

[0020] The reverse point confirmation unit receives the high-definition image after the abnormal area is marked, and confirms the reverse area in the opposite direction from the marked abnormal area, and uses the corresponding high-definition image acquisition equipment to acquire the high-definition point image of the corresponding reverse area, and transmits the acquired high-definition point image to the diffusion parameter analysis unit;

[0021] The diffusion parameter analysis unit confirms the hole position inside the back area according to the collected high-definition point image of the back area, confirms the diffusion degree of the two groups of winding wires at the inner edge of the hole position, confirms the diffusion parameter belonging to the corresponding hole position, generates a diffusion interval, and transmits the confirmed diffusion interval to the standard error confirmation unit. The specific method of generating the diffusion interval is:

[0022] From the high-definition point image of the reverse area, confirm each hole position and the winding wires on both sides of the lower end of the corresponding hole position, and combine the hole position and the corresponding winding wire with the two-dimensional coordinate system;

[0023] Mark the winding wire on the lower side of the hole as one side of the wire, then confirm the center point of the lower end of the one side of the wire and the intersection with the hole, confirm the point coordinates of the center point and the intersection, and construct the quadratic equation Y=AX belonging to this curve based on the point coordinates of the two points 2+B, confirm the A value, and mark the confirmed A value of different wells as A 1t and A 2t , where t is a different hole position, and the subscript 1t or 2t represents that there are two sets of A values ​​in the corresponding hole position, and the larger the A value, the lower the expansion degree of the thread, and the smaller the A value, the greater the expansion degree of the thread;

[0024] From the confirmed A values, identify the minimum and maximum values ​​and mark them as diffusion intervals [A tmin , A tmax ], the confirmed diffusion interval [A tmin , A tmax ] is transmitted to the standard deviation confirmation unit;

[0025] The standard deviation confirmation unit, for the diffusion interval [A tmin , A tmax ] is received and the interval difference is confirmed. According to the confirmed difference, whether the reverse side of the abnormal area is abnormal is determined, and a reverse side test abnormal signal is generated. The specific method of performing the analysis is as follows:

[0026] Using Ac=A tmax -A tmin Obtain the corresponding difference value Ac of the diffusion interval, and compare the confirmed difference value Ac with the preset parameter Ys, where Ys is the preset value;

[0027] When Ac<Ys, the detection signal generating unit generates a negative test normal signal, otherwise, the detection signal generating unit generates a negative test abnormal signal.

[0028] The present invention provides an intelligent evaluation system for tensile properties of down jacket fabrics based on big data analysis. Compared with the prior art, it has the following beneficial effects:

[0029] The present invention uses the front analysis end and the back analysis end to conduct in-depth detection of the abnormal area from different angles; the front analysis end constructs an abnormal center circle and an outer circle, accurately analyzes the spacing parameters of the hole positions between the two groups of circles, and can accurately determine whether the front test of the abnormal area is normal; the back analysis end confirms the diffusion degree of the winding silk thread inside the hole position of the back area, generates a diffusion interval and performs standard deviation confirmation, and comprehensively evaluates the back test situation of the abnormal area, thereby realizing an all-round and three-dimensional evaluation of the tensile performance of the down jacket fabric;

[0030] After the detection signal generation unit generates an abnormal signal based on the front and back side analysis results, the abnormal cause determination unit can further analyze the root cause of the abnormality; for example, the front side test abnormality may be related to the fabric thread splicing process and uneven force during the stretching process; the back side test abnormality may be related to the thread quality, winding method, etc., which provides a precise direction for problem troubleshooting and improvement in the production process, helps to optimize the production process and improve the quality of down jacket fabrics. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a schematic diagram of the principle framework of the present invention;

[0032] Figure 2 Schematic diagram of generating the negative test signal of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] First embodiment

[0035] See also Figure 1 , the present application provides an intelligent evaluation system for tensile properties of down jacket fabrics based on big data analysis, including a high-definition image acquisition terminal, a detection center, and a display unit, wherein the high-definition image acquisition terminal, the detection center, and the display unit are electrically connected from an output node to an input node in sequence;

[0036] Wherein, the detection center includes a different area confirmation unit, a storage unit, a front side analysis end, a back side analysis end, a detection signal generating unit and an abnormal cause determination unit, wherein the storage unit is electrically connected to the input end of the different area confirmation unit, the different area confirmation unit is electrically connected to the input nodes of the front side analysis end and the back side analysis end respectively, the front side analysis end includes an analysis graph construction unit and a spacing parameter analysis unit, wherein the analysis graph construction unit is electrically connected to the spacing parameter analysis unit input node, the back side analysis end includes a back side point position confirmation unit, a diffusion parameter analysis unit and a standard deviation confirmation unit, wherein the back side point position confirmation unit is electrically connected to the diffusion parameter analysis unit input node, the diffusion parameter analysis unit is electrically connected to the standard deviation confirmation unit input node, the front side analysis end and the back side analysis end are both electrically connected to the detection signal generating unit input node, the detection signal generating unit is electrically connected to the abnormal cause determination unit input node, and the abnormal cause determination unit is electrically connected to the display unit input node;

[0037] Its high-definition image acquisition end acquires high-definition images of the surface of the down jacket fabric involved in the tensile performance test, and transmits the acquired high-definition images to the different-area confirmation unit. When performing the tensile performance test, it is generally only for a single piece of down jacket fabric, and it is necessary to clamp the down jacket fabric with the set clamping setting, and set the specified tensile test force to perform the tensile test on the down jacket fabric;

[0038] The out-of-area confirmation unit compares the acquired high-definition image with the complete image preset in the storage unit, confirms the abnormal part of the comparison and performs specific calibration of the abnormal area. The calibration method is:

[0039] Identify the spacing between several streaks from the acquired high-definition image, and compare the confirmed spacing with the complete image preset in the storage unit to identify whether the spacing at the streaks at the same position is consistent. If the comparison results are consistent, no processing is required. If the comparison results are inconsistent, the abnormal comparison point is marked as an abnormal area. Specifically, based on the pixel value of the corresponding point in the image, the existing streaks in the corresponding high-definition image can be locked. The pixel features associated with the spacing points between the fabrics and the silk threads are all different. Since the method for determining the corresponding pixel features is relatively common in the prior art, it will not be described in detail here. Based on the corresponding comparison process, the specific area of ​​the corresponding comparison abnormality can be locked;

[0040] The front analysis end re-analyzes the high-definition image associated with the abnormal area to identify whether the front test of the abnormal area is normal. The specific execution ends are the analysis graphic construction unit and the spacing parameter analysis unit.

[0041] The analysis graph construction unit receives the high-definition image after the abnormal area is marked, analyzes the marked high-definition image, intercepts the analysis graph from the high-definition image, and transmits the intercepted analysis graph to the spacing parameter analysis unit. The specific method of performing the analysis is as follows:

[0042] Confirm the marked abnormal area from the high-definition image, confirm the maximum value of the distance between several points on the edge of the abnormal area, and use this maximum value as the diameter to construct a set of abnormal center circles;

[0043] Then radiate the abnormal center circle around it, and the radiation parameter is X1cm, where X1 is a preset value, and its specific value is determined by the operator based on experience, and X1 takes the value of 2, to obtain a set of outer circles;

[0044] According to the confirmed abnormal center circle and outer circle, the high-definition image is directly intercepted, the regional graphics belonging to the outer circle are directly intercepted and marked as analysis graphics, and the analysis graphics are transmitted to the spacing parameter analysis unit;

[0045] Specifically, in order to analyze the specific abnormal situation of the abnormal area, it is necessary to compare the abnormal area with the surrounding normal area, and determine the specific abnormal situation through the comparison result, so as to make corresponding response measures.

[0046] The spacing parameter analysis unit analyzes the abnormal center circle and the outer circle in the analysis graph to determine the spacing parameters of the holes between the two groups of circles. According to the specific comparison results, it is confirmed whether the positive test of the abnormal area is normal. The specific method of performing the analysis is as follows:

[0047] Confirm the several micropores in the abnormal center circle, confirm the distance parameters between the diagonal points in the micropores, and mark the confirmed distance parameters as J i , where i represents different micropores in the abnormal center circle. In the textile, the corresponding lines are spliced ​​together. During the splicing process, there will be corresponding points between adjacent interlaced line segments when testing. During the test, the corresponding textile has a certain stretching condition. In order to ensure that the test results are more accurate, the textile needs to be stretched, and the stretching value is limited;

[0048] Similarly, several micropores within the outer circle of the high-definition image are confirmed, and the distance parameters between the diagonal points in the micropores are confirmed, and the confirmed distance parameters are marked as J k , where k represents the different micropores in the outer circle;

[0049] The two different sets of distance parameters are processed by averaging to obtain the mean JJ belonging to Ji i , get the value belonging to J k The mean value of JJ k , when JJ i >JJ k ×1.3, the positive test abnormal signal is generated by the detection signal generation unit. i ≤JJ k ×1.3, a positive test normal signal is generated by the detection signal generation unit, where 1.3 is the set fluctuation value;

[0050] Among them, the reverse side analysis end, based on the high-definition image associated with the abnormal area, locks the reverse side area of ​​the back, and based on the regional image of the reverse side area, identifies whether the reverse side test of the abnormal area is normal. The specific execution ends are the reverse side point confirmation unit, the diffusion parameter analysis unit and the standard deviation confirmation unit;

[0051] The reverse point confirmation unit receives the high-definition image after the abnormal area is marked, and confirms the reverse area in the opposite direction from the marked abnormal area, and uses the corresponding high-definition image acquisition equipment to acquire the high-definition point image of the corresponding reverse area, and transmits the acquired high-definition point image to the diffusion parameter analysis unit;

[0052] The diffusion parameter analysis unit confirms the hole position inside the back area according to the collected high-definition point image of the back area, confirms the diffusion degree of the two groups of winding wires at the inner edge of the hole position, confirms the diffusion parameters belonging to the corresponding hole position, generates a diffusion interval, and transmits the confirmed diffusion interval to the standard error confirmation unit. The specific method of determining the diffusion interval is as follows:

[0053] From the high-definition point image of the reverse area, confirm each hole position and the winding wires on both sides of the lower end of the corresponding hole position, and combine the hole position and the corresponding winding wire with the two-dimensional coordinate system;

[0054] Mark the winding wire on the lower side of the hole as one side of the wire, then confirm the center point of the lower end of the one side of the wire and the intersection with the hole, confirm the point coordinates of the center point and the intersection, and construct the quadratic equation Y=AX belonging to this curve based on the point coordinates of the two points 2 +B, confirm the A value, and mark the confirmed A value of different wells as A 1t and A 2t , where t is a different hole position, and the subscript 1t or 2t represents that there are two sets of A values ​​in the corresponding hole position, and the larger the A value, the lower the expansion degree of the thread, and the smaller the A value, the greater the expansion degree of the thread;

[0055] From the confirmed A values, identify the minimum and maximum values ​​and mark them as diffusion intervals [A tmin , A tmax ], the confirmed diffusion interval [A tmin , A tmax ] is transmitted to the standard deviation confirmation unit;

[0056] In the corresponding hole position, there will be corresponding silk threads at the lower end, one on one side and the other on the other side. The quadratic equations corresponding to the silk threads on one side and the other side are different, so different silk threads correspond to different A values. The so-called A value can directly reflect the expansion degree of the corresponding silk thread and the loose state of the silk thread. The larger the A value, the tighter the silk thread, and the smaller the A value, the looser the silk thread.

[0057] Combination Figure 2 , standard deviation confirmation unit, for the diffusion interval [A tmin , A tmax] is received and the interval difference is confirmed. According to the confirmed difference, whether the reverse side of the abnormal area is abnormal is determined, and a reverse side test abnormal signal is generated. The specific method of performing the analysis is as follows:

[0058] Using Ac=A tmax -A tmin Obtain the corresponding difference Ac of the diffusion interval, and compare the confirmed difference Ac with the preset parameter Ys, where Ys is a preset value, and its specific value is determined by the operator based on experience;

[0059] When Ac<Ys, the detection signal generating unit generates a negative test normal signal, otherwise, the detection signal generating unit generates a negative test abnormal signal.

[0060] Second embodiment

[0061] This embodiment is a further embodiment of the first embodiment, and is for displaying the abnormal causes associated with the corresponding signals.

[0062] The abnormality cause determination unit generates a specific determination cause according to the received specific signal, wherein the specific manner of generating the determination cause is:

[0063] The received signals are the front test abnormality signal and the back test abnormality signal, and the wire breakage reason is generated and transmitted to the display unit;

[0064] When the received signal is a positive test abnormal signal or a reverse test abnormal signal, the reason for the yarn being too loose is generated and displayed directly;

[0065] If the received signals are all normal signals, no processing is required.

[0066] Some of the data in the above formulas are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0067] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An intelligent evaluation system for tensile properties of down jacket fabrics based on big data analysis, characterized in that: include: The high-definition image acquisition terminal acquires high-definition images of the surface of the down jacket fabric involved in the tensile performance test and transmits them to the testing center; The testing center performs fabric tension detection on high-definition images and confirms abnormal signal display based on the detection results. The testing center includes a different area confirmation unit, a storage unit, a front analysis end, and a back analysis end: The out-of-area confirmation unit compares the acquired high-definition image with the complete image preset in the storage unit, confirms the abnormal part of the comparison and performs specific calibration of the abnormal area; The front analysis end re-analyzes the high-definition image associated with the abnormal area to identify whether the front test of the abnormal area is normal. The specific execution ends are the analysis graphic construction unit and the spacing parameter analysis unit. The reverse side analysis end, based on the high-definition image associated with the abnormal area, locks the reverse side area of ​​the back, and based on the regional image of the reverse side area, identifies whether the reverse side test of the abnormal area is normal. The specific execution ends are the reverse side point confirmation unit, the diffusion parameter analysis unit and the standard deviation confirmation unit.

2. The intelligent evaluation system for tensile properties of down jacket fabrics based on big data analysis according to claim 1 is characterized in that: The specific method of the out-of-area confirmation unit to calibrate the abnormal area is: The spacing between several streaks is identified from the acquired high-definition image, and the confirmed spacing is compared with the preset complete image in the storage unit to identify whether the spacing at the streaks in the same position is consistent. If the comparison results are consistent, no processing is required. If the comparison results are inconsistent, the abnormal comparison point will be marked as an abnormal area.

3. The intelligent evaluation system for tensile properties of down jacket fabrics based on big data analysis according to claim 1 is characterized in that: The analysis graph construction unit receives the high-definition image after the abnormal area is marked, analyzes the marked high-definition image, intercepts the analysis graph from the high-definition image, and transmits the intercepted analysis graph to the spacing parameter analysis unit.

4. The intelligent evaluation system for tensile properties of down jacket fabrics based on big data analysis according to claim 3 is characterized in that: The specific method of the analysis graph construction unit to intercept the analysis graph is: Confirm the marked abnormal area from the high-definition image, confirm the maximum value of the distance between several points on the edge of the abnormal area, and use this maximum value as the diameter to construct a set of abnormal center circles; Then radiate the abnormal center circle around the periphery with a radiation parameter of X1 cm, where X1 is a preset value, to obtain a set of outer circles; According to the confirmed abnormal center circle and outer circle, the high-definition image is directly intercepted, the area graphic belonging to the outer circle is directly intercepted and marked as an analysis graphic, and the analysis graphic is transmitted to the spacing parameter analysis unit.

5. The intelligent evaluation system for tensile properties of down jacket fabrics based on big data analysis according to claim 4 is characterized in that: The spacing parameter analysis unit analyzes the abnormal central circle and the outer circle in the analysis graph, determines the spacing parameters of the hole positions between the two groups of circles, and confirms whether the positive test of the abnormal area is normal based on the specific comparison results.

6. The intelligent evaluation system for tensile properties of down jacket fabrics based on big data analysis according to claim 5 is characterized in that: The specific method of the spacing parameter analysis unit to confirm whether the positive test of the abnormal area is normal is: Confirm the several micropores in the abnormal center circle, confirm the distance parameters between the diagonal points in the micropores, and mark the confirmed distance parameters as J i , where i represents different micropores within the abnormal center circle; Then confirm several micropores in the outer circle of the high-definition image, confirm the distance parameters between the diagonal points in the micropores, and mark the confirmed distance parameters as J k , where k represents the different micropores in the outer circle; The two different sets of distance parameters are processed by averaging to obtain the mean JJ belonging to Ji i , get the value belonging to J k The mean value of JJ k , when JJ i >JJ k ×1.3, the positive test abnormal signal is generated by the detection signal generation unit. i ≤JJ k ×1.3, a positive test normal signal is generated by the detection signal generation unit.

7. The intelligent evaluation system for tensile properties of down jacket fabrics based on big data analysis according to claim 1 is characterized in that: The reverse side point confirmation unit receives the high-definition image after the abnormal area is marked, and confirms the reverse side area in the opposite direction from the marked abnormal area, and uses the corresponding high-definition image acquisition equipment to acquire the high-definition point image of the corresponding reverse side area, and transmits the acquired high-definition point image to the diffusion parameter analysis unit.

8. The intelligent evaluation system for tensile properties of down jacket fabrics based on big data analysis according to claim 7 is characterized in that: The diffusion parameter analysis unit confirms the hole positions inside the back area based on the collected high-definition point image of the back area, confirms the diffusion degree of the two groups of winding wires at the inner edge of the hole positions, confirms the diffusion parameters belonging to the corresponding hole positions, generates a diffusion interval, and transmits the confirmed diffusion interval to the standard deviation confirmation unit.

9. The intelligent evaluation system for tensile properties of down jacket fabrics based on big data analysis according to claim 8 is characterized in that: The specific method of the diffusion parameter analysis unit generating the diffusion interval is: From the high-definition point image of the reverse area, confirm each hole position and the winding wires on both sides of the lower end of the corresponding hole position, and combine the hole position and the corresponding winding wire with the two-dimensional coordinate system; Mark the winding wire on the lower side of the hole as one side of the wire, then confirm the center point of the lower end of the one side of the wire and the intersection with the hole, confirm the point coordinates of the center point and the intersection, and construct the quadratic equation Y=AX belonging to this curve based on the point coordinates of the two points 2 +B, confirm the A value, and mark the confirmed A value of different wells as A 1t and A 2t , where t is a different hole position, and the subscript 1t or 2t represents that there are two sets of A values ​​in the corresponding hole position, and the larger the A value, the lower the expansion degree of the thread, and the smaller the A value, the greater the expansion degree of the thread; From the confirmed A values, identify the minimum and maximum values ​​and mark them as diffusion intervals [A tmin , A tmax ], the confirmed diffusion interval [A tmin , A tmax ] is transmitted to the standard deviation confirmation unit.

10. The intelligent evaluation system for tensile properties of down jacket fabrics based on big data analysis according to claim 9 is characterized in that: The standard deviation confirmation unit, for the diffusion interval [A tmin , A tmax ] is received and the interval difference is confirmed. According to the confirmed difference, whether the reverse side of the abnormal area is abnormal is determined, and a reverse side test abnormal signal is generated. The specific method of performing the analysis is as follows: Using Ac=A tmax -A tmin Obtain the corresponding difference value Ac of the diffusion interval, and compare the confirmed difference value Ac with the preset parameter Ys, where Ys is the preset value; When Ac<Ys, the detection signal generating unit generates a negative test normal signal, otherwise, the detection signal generating unit generates a negative test abnormal signal.

Images