Intelligent detection method and system based on defects of spinning spinneret plate

Abstract

The invention relates to an intelligent detection method and system based on defects of a spinning spinneret plate, and relates to the technical field of textile production, and the method comprises the following steps: obtaining the type and number of detection products; determining product specification parameters according to the detected product type; forming a product type combination in the detection product types, and analyzing and defining an effective type combination according to product specification parameters and detection areas in the product type combination; randomly generating a type combination number according to each effective type combination so as to match the effective type combinations to construct an overall detection scheme, and determining an overall detection frequency; determining each simulation detection quantity according to the type combination quantity and the effective type combination, and defining an effective detection scheme according to the simulation detection quantity and the detection product quantity; and defining the effective detection scheme corresponding to the minimum overall detection frequency as a use detection scheme to detect each spinning spinneret plate. The device has the effect of improving the overall detection efficiency during the blockage detection of the spinning spinneret plate.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of textile production technology, in particular to an intelligent detection method and system based on spinning nozzle plate defects. BACKGROUND

[0002] The spinning nozzle plate is a core component in the chemical fiber spinning equipment, and a large number of micron-sized holes are distributed on its surface. After the molten polymer is extruded through the spinning hole, continuous fibers are formed. The hole state of the spinning nozzle plate directly affects the uniformity, strength and spinning stability of the fibers. Therefore, defect detection of the spinning nozzle plate is crucial. Among them, hole blockage is the most common defect type, which may cause spinning breakage, uneven fineness, etc., and seriously affect production efficiency and product quality.

[0003] At present, the blockage detection of the spinning nozzle plate mainly relies on manual operation. Usually, the spinning nozzle plate is disassembled by the staff and placed on a light transmission plate. The light transmission principle is used to observe the hole light transmission condition, and visual recognition is used to judge whether there is blockage.

[0004] In the above related technology, due to the various specifications and sizes of the spinning nozzle plate, it needs to be placed, adjusted and observed one by one during detection, which leads to a long overall detection process and is difficult to meet the needs of large-scale production, and there is still room for improvement. SUMMARY

[0005] In order to improve the overall detection efficiency of the spinning nozzle plate blockage detection, the present application provides an intelligent detection method and system based on spinning nozzle plate defects.

[0006] In the first aspect, the present application provides an intelligent detection method based on spinning nozzle plate defects, which adopts the following technical scheme: An intelligent detection method based on spinning nozzle plate defects, comprising: Obtaining the detection product type and the detection product quantity; According to the preset type matching relationship, the product specification parameters corresponding to the detection product type are determined; Randomly selecting any number of detection product types from each detection product type to form a product type combination, and analyzing and determining the product placement state according to the product specification parameters of the detection product types in the product type combination and the preset detection area, and defining the product type combination with the same product placement state as the preset effective placement state as the effective type combination; According to each effective type combination, the number of type combinations is randomly generated, and the overall detection scheme is constructed according to the effective type combination and the number of type combinations, and the summation calculation is performed according to the number of each type combination in the overall detection scheme to determine the overall detection times; The simulation detection quantity of each detection product type is determined according to the type combination quantity and the corresponding effective type combination in the overall detection scheme, and the overall detection scheme in which each simulation detection quantity is consistent with the corresponding detection product quantity is defined as an effective detection scheme; The overall detection times with the minimum value is determined according to the preset sorting rule, and the effective detection scheme corresponding to the overall detection times is defined as a use detection scheme, and each spinning nozzle is detected according to the use detection scheme.

[0007] Optionally, the step of randomly selecting any quantity of detection product types in each detection product type to form the product type combination comprises: The hole region coverage area is determined according to the product specification parameter, and the product type order is determined according to the hole region coverage area from large to small in each detection product type from front to back; The first detection product type in the product type order is defined as a head product type, and the head upper limit quantity is determined by calculating the hole region coverage area of the head product type and the preset detection area; The head quantity is randomly selected within the head upper limit quantity, and the head occupied area is determined by calculating the head quantity and the corresponding hole region coverage area; The detection area is updated by calculating the detection area and the head occupied area, and the head product type is removed from the product type order to update the head product type; The product type combination is constructed by combining the corresponding head quantity of all detection product types.

[0008] Optionally, the step of determining the product placement state by analyzing the product specification parameter of the detection product type in the product type combination and the preset detection area comprises: The center virtual point and the virtual placement orientation of each product in the detection area are randomly generated in the product type combination, and the virtual placement scheme is constructed by combining the center virtual point and the virtual placement orientation of all products; The product placement area is simulated and generated in the detection area according to the product specification parameter, the center virtual point and the virtual placement orientation, and the waiting hole region is determined in the product placement area; The virtual placement scheme in which all waiting hole regions are in the detection area and there is no overlapping waiting hole region is defined as a reasonable placement scheme; It is judged whether there is at least one reasonable placement scheme in a single product type combination; If there is at least one reasonable placement scheme in a single product type combination, the effective placement state is determined as the product placement state; If there is no at least one reasonable placement scheme for the single product type combination, a preset invalid placement state is determined as the product placement state.

[0009] Optionally, after the reasonable placement scheme is determined, the intelligent detection method based on the spinneret defects further comprises: According to each product placement area, a product overlap area is determined, and according to each product overlap area, an overlap area is determined; The product on the product placement area with the product overlap area is defined as an overlap product, and the overlap product is counted to determine an overlap number; The sum of each overlap area is calculated to determine an overall overlap area, and the overlap number and the overall overlap area are calculated to determine a scheme suitability; According to the sorting rule, the largest numerical value of the scheme suitability is determined, and the reasonable placement scheme corresponding to the largest scheme suitability is defined as the use placement scheme, and each spinneret is placed according to the use placement scheme when detecting each spinneret.

[0010] Optionally, after the scheme suitability is determined, the intelligent detection method based on the spinneret defects further comprises: Determine whether there is at least two reasonable placement schemes with the same and largest scheme suitability; If there is no at least two reasonable placement schemes with the same and largest scheme suitability, the reasonable placement scheme corresponding to the largest scheme suitability is defined as the use placement scheme; If there is at least two reasonable placement schemes with the same and largest scheme suitability, the reasonable placement scheme corresponding to the largest scheme suitability is defined as the alternative placement scheme; In the alternative placement scheme, the hole center position is determined according to the waiting hole area, and the shooting separation distance is determined according to the hole center position and the preset detection shooting center; According to all shooting separation distances, the effective shooting parameters are calculated, and the alternative placement scheme corresponding to the largest numerical value of the effective shooting parameters is defined as the use placement scheme.

[0011] Optionally, after the overall detection number is determined, the intelligent detection method based on the spinneret defects further comprises: Determine whether there is at least two effective detection schemes with the same and smallest overall detection number; If there is no at least two effective detection schemes with the same and smallest overall detection number, the effective detection scheme corresponding to the smallest overall detection number is defined as the use detection scheme; If there is at least two effective detection schemes with the same and smallest overall detection number, the effective detection scheme corresponding to the smallest overall detection number is defined as the alternative detection scheme; counting according to different effective type combinations in the alternative detection scheme to determine the number of combination types; calculating according to the scheme fitness of each effective type combination, the number of type combinations and the number of combination types in the alternative detection scheme to determine the detection rationality parameter; determining the detection rationality parameter with the largest numerical value according to the sorting rule, and defining the alternative detection scheme corresponding to the detection rationality parameter as the use detection scheme.

[0012] Optionally, when detecting each spinning nozzle according to the use detection scheme, the intelligent detection method based on spinning nozzle defects further comprises: acquiring the historical defect threshold of each detection product type; determining the real-time defect rate according to each detection product type; outputting a detection abnormal signal when the real-time defect rate is greater than the historical defect threshold.

[0013] In a second aspect, the application provides an intelligent detection system based on spinning nozzle defects, which adopts the following technical scheme: An intelligent detection system based on spinning nozzle defects, comprising: an acquisition module, configured to acquire the detection product type and the detection product quantity; a processing module, connected with the acquisition module, configured to store and process information; the processing module determines the product specification parameter corresponding to the detection product type according to the preset type matching relationship; the processing module randomly selects any number of detection product types in each detection product type to form a product type combination, and analyzes and determines the product placement state according to the product specification parameter of the detection product type in the product type combination and the preset detection area, and defines the product type combination with the same product placement state as the preset effective placement state as an effective type combination; the processing module randomly generates the number of type combinations according to each effective type combination, constructs an overall detection scheme according to the effective type combination and the number of type combinations, and determines the overall detection times by summing calculation according to the number of type combinations in the overall detection scheme; the processing module determines the simulation detection quantity of each detection product type according to the number of type combinations and the corresponding effective type combination in the overall detection scheme, and defines the overall detection scheme with each simulation detection quantity being consistent with the corresponding detection product quantity as an effective detection scheme; the processing module determines the overall detection times with the smallest numerical value according to the preset sorting rule, defines the effective detection scheme corresponding to the overall detection times as the use detection scheme, and detects each spinning nozzle according to the use detection scheme.

[0014] In summary, the present application includes at least one of the following beneficial technical effects: In the process of detecting the defects of the spinning nozzle plate, each type of spinning nozzle plate is analyzed to reasonably distribute each spinning nozzle plate, so that multiple spinning nozzle plates can be detected at the same time as much as possible, to meet the defect detection requirements and improve the overall detection efficiency. In the process of distributing the spinning nozzle plate, the hole overlapping condition of the spinning nozzle plate to be detected is fully considered to improve the rationality of the distribution and improve the detection effect. BRIEF DESCRIPTION OF DRAWINGS

[0015] Fig. 1 is a flowchart of the intelligent detection method based on the defects of the spinning nozzle plate.

[0016] Fig. 2 is a module flowchart of the intelligent detection method based on the defects of the spinning nozzle plate. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical scheme and advantages of the present application more clear, the present application will be further described in detail below with reference to the drawings Figs. 1-2 and examples. It should be understood that the specific examples described herein are only used to explain the present application and do not limit the present application.

[0018] The embodiments of the present application will be described in further detail below with reference to the drawings of the specification.

[0019] The embodiments of the present application disclose an intelligent detection method based on the defects of the spinning nozzle plate, with reference to Fig. 1 The method flowchart of the intelligent detection method based on the defects of the spinning nozzle plate includes the following steps: Step S100: Obtain the detection product type and the detection product quantity.

[0020] The detection product type is the type of the spinning nozzle plate to be detected, such as 36H-Y3, 16H-SS, etc., and the detection product quantity is the quantity of the spinning nozzle plate to be detected. Different types of spinning nozzle plates correspond to different quantities, and both are manually input by the staff.

[0021] Step S101: Determine the product specification parameter corresponding to the detection product type according to the preset type matching relationship.

[0022] The product specification parameter is the model parameter of the spinning nozzle plate, including the number of holes, the size, the specific shape, etc. Different detection product types correspond to different product specification parameters, and the type matching relationship between them is recorded and stored by the staff in advance.

[0023] Step S102: randomly selecting any number of detection product types in each detection product type to form a product type combination, and analyzing the product placement state according to the product specification parameters of the detection product types in the product type combination and the preset detection area, and defining the product type combination with the product placement state consistent with the preset effective placement state as an effective type combination.

[0024] The product type combination is a combination with a spinning nozzle plate formed after randomly selecting any number of each detection product type. For example, there are three types of spinning nozzle plates, marked as A / B / C respectively. The corresponding product type combination can be 1A / 2B / 2C, that is, there is one A type spinning nozzle plate, two B type spinning nozzle plates, and two C type spinning nozzle plates in the current product type combination. The detection area is the area where the light transmission plate is located, that is, the area where the hole blockage of the spinning nozzle plate can be detected by visual recognition. The product placement state is the state of whether all products in the product type combination can be placed in the detection area. The state includes the effective placement state in which all products can be placed and the invalid placement state in which all products cannot be placed. For details, see steps S300-S3032. When the product placement state is consistent with the effective placement state, it means that all products can be detected simultaneously under the current product type combination. Therefore, the effective type combination is defined to be identified for subsequent analysis.

[0025] Step S103: generating a type combination number according to each effective type combination, and constructing an overall detection scheme according to the effective type combination and the type combination number, and calculating the sum of each type combination number in the overall detection scheme to determine the overall detection times.

[0026] The type combination number is the number of simulated single effective type combination that needs to be processed. The overall detection scheme is a scheme for detecting all simulated type combination number of effective type combinations. The overall detection times are the total number of detections required when detecting the generated type combination number of effective type combinations, which is determined by summing all type combination numbers.

[0027] Step S104: determining the simulation detection number of each detection product type according to the type combination number and the corresponding effective type combination in the overall detection scheme, and defining the overall detection scheme in which each simulation detection number is consistent with the corresponding detection product number as an effective detection scheme.

[0028] The simulation detection quantity is the quantity corresponding to a single detection product type. When each simulation detection quantity is consistent with the corresponding detection product quantity, it indicates that the current overall detection scheme can detect all the spinning jet plates that need to be detected. Therefore, an effective detection scheme is defined to distinguish different overall detection schemes for subsequent analysis.

[0029] Step S105: Determine the overall detection quantity with the smallest value according to the preset sorting rule, and define the effective detection scheme corresponding to the overall detection quantity as the use detection scheme. Then, detect each spinning jet plate according to the use detection scheme.

[0030] The sorting rule is a method set by the staff to sort the values, such as the bubble sort method. Through the sorting rule, the overall detection quantity with the smallest value can be determined, that is, the number of detections required in the current effective detection scheme is the least, that is, the detection efficiency is the highest. Therefore, it is defined as the use detection scheme for subsequent spinning jet plate detection.

[0031] The step of randomly selecting any number of detection product types from each detection product type to form a product type combination includes: Step S200: Determine the hole area coverage according to the product specification parameters, and sort each detection product type from front to back according to the hole area coverage from large to small to determine the product type order.

[0032] The hole area coverage is the area of the region on the product that cannot overlap with other products, that is, the area of the region where the holes are located on the product, which is directly obtained in the product specification parameters. The product type order is the order obtained by sorting each type of product according to the hole area coverage from large to small.

[0033] Step S201: Define the first detection product type in the product type order as the head product type, and calculate the head upper limit quantity according to the hole area coverage of the head product type and the preset detection area.

[0034] The head product type is defined to distinguish the product type with the highest area requirement. The detection area is the area of the detection region. The head upper limit quantity is the maximum number of products of the head product type that can appear in the detection region without affecting the hole detection under the theoretical condition, which is determined by dividing the detection area by the hole area coverage of the head product type and taking the integer result.

[0035] Step S202: Randomly select the head quantity within the head upper limit quantity, and calculate the head occupied area according to the head quantity and the corresponding hole area coverage.

[0036] The header quantity is the number of products of the header product type that needs to be processed in simulation, the header quantity is not greater than the header upper limit quantity, the header occupied area is the minimum area that the products of the header product type in the header quantity need to occupy in a theoretical case, and the header occupied area is determined by multiplying the header quantity by the corresponding hole area coverage area.

[0037] Step S203: calculating to update the detection area according to the detection area and the header occupied area, and removing the header product type in the product type order to update the header product type.

[0038] By subtracting the header occupied area from the detection area, the area of the region available for the remaining types of products to be placed can be obtained, and by removing the header product type, the header product type can be re-determined, thereby realizing analysis of the remaining detection product types.

[0039] Step S204: combining all detection product types corresponding to the header quantity to construct a product type combination.

[0040] All detection product types as header product types will have a corresponding header quantity, and according to the relationship between the header quantity and the detection product type, a product type combination that can be placed in the detection area in a theoretical case can be constructed, thereby reducing the analysis of invalid product type combinations, reducing the amount of data analysis to improve overall computing efficiency.

[0041] The step of analyzing and determining the product placement state according to the product specification parameters of the detection product types in the product type combination and the preset detection area comprises: Step S300: generating a center virtual point and a virtual placement orientation for each product in the product type combination in the detection area, and combining the center virtual points and the virtual placement orientations of all products to construct a virtual placement scheme.

[0042] The center virtual point is a position point that needs to be placed in the detection area, and the virtual placement orientation is the orientation in which the product needs to be placed in the detection area. By constructing the center virtual point and the virtual placement orientation, the actual occupied area of the product in the detection area can be simulated and analyzed; the virtual placement scheme is the scheme obtained after each product is simulated and placed.

[0043] Step S301: simulating and generating a product placement area in the detection area according to the product specification parameters, the center virtual point and the virtual placement orientation, and determining a waiting hole area in the product placement area.

[0044] The product placement area, i.e., the product of a single detection product type, places a preset fixed point on the central virtual point, and the direction is according to the virtual placement area occupied after placement, and the waiting hole area, i.e., the area where the hole to be detected on the product placement area is located, can be positioned by the product specification parameters to determine.

[0045] Step S302: define the virtual placement scheme in which all waiting hole areas are in the detection area and there is no overlapping of waiting hole areas as a reasonable placement scheme.

[0046] When all waiting hole areas are in the detection area and there is no overlapping of waiting hole areas, it means that all products can be detected simultaneously under the current virtual placement scheme, so a reasonable placement scheme is defined to distinguish different virtual placement schemes for subsequent analysis.

[0047] Step S303: determine whether there is at least one reasonable placement scheme for a single product type combination.

[0048] The purpose of the determination is to know whether the currently constructed product type combination can meet the requirement of simultaneous detection of the spinning nozzle.

[0049] Step S3031: if there is at least one reasonable placement scheme for a single product type combination, determine the effective placement state as the product placement state.

[0050] When there is at least one reasonable placement scheme for a single product type combination, it means that the current product type combination can meet the requirement of simultaneous detection of the spinning nozzle, so the effective placement state is determined as the product placement state.

[0051] Step S3032: if there is no at least one reasonable placement scheme for a single product type combination, determine the preset invalid placement state as the product placement state.

[0052] When there is no at least one reasonable placement scheme for a single product type combination, it means that the current product type combination cannot meet the requirement of simultaneous detection of the spinning nozzle, so the invalid placement state is determined as the product placement state.

[0053] After determining the reasonable placement scheme, the intelligent detection method based on spinning nozzle defects further comprises: Step S400: determine the product overlap area according to each product placement area, and determine the overlap area according to each product overlap area.

[0054] The product overlap area is the area where the product placement areas overlap, and the overlap area is the area of a single product overlap area.

[0055] Step S401: define the product existing in the product overlapping area on the product placement area as an overlapping product, and count the overlapping products to determine the overlapping number.

[0056] The overlapping product is defined to distinguish different products, and the overlapping number is the total number of overlapping products determined under the current reasonable placement scheme.

[0057] Step S402: sum up the area of each overlapping area to determine the total overlapping area, and calculate the scheme suitability according to the overlapping number and the total overlapping area.

[0058] The total overlapping area is the sum of the areas of all determined overlapping areas, and the scheme suitability is a parameter reflecting whether the current reasonable placement scheme can be better applied to defect detection. The larger the value is, the more conducive to the defect detection of the spinning nozzle. The calculation formula is wherein is the scheme suitability, is the overlapping number, is the total overlapping area, is a fixed calculation parameter for adjusting the scheme suitability, is a fixed calculation parameter reflecting the importance of the overlapping number compared to the scheme suitability, is a fixed calculation parameter reflecting the importance of the total overlapping area compared to the scheme suitability.

[0059] Step S403: determine the scheme suitability with the largest value according to the sorting rule, and define the reasonable placement scheme corresponding to the scheme suitability as the use placement scheme, and place each spinning nozzle according to the use placement scheme when detecting each spinning nozzle.

[0060] The sorting rule can determine the scheme suitability with the largest value, that is, the reasonable placement scheme corresponding to the scheme suitability is the most convenient for detecting each spinning nozzle. Therefore, it is defined as the use placement scheme to distinguish different reasonable placement schemes. In the subsequent process of detecting the spinning nozzle, the product is placed according to the use placement scheme for the current product type combination, thereby improving the overall detection effect.

[0061] After determining the scheme suitability, the intelligent detection method for the spinning nozzle defect further comprises: Step S500: determine whether there are at least two reasonable placement schemes with the same maximum scheme suitability.

[0062] The purpose of the determination is to know whether there are multiple reasonable placement schemes meeting the requirements, so as to determine the unique reasonable placement scheme.

[0063] Step S5001: If there is no at least two reasonable placement schemes with the same maximum scheme fitness, define the reasonable placement scheme corresponding to the maximum scheme fitness as the use placement scheme.

[0064] When there is no at least two reasonable placement schemes with the same maximum scheme fitness, it means that there is only one reasonable placement scheme that meets the requirements, and at this time it can be defined as the use placement scheme.

[0065] Step S5002: If there are at least two reasonable placement schemes with the same maximum scheme fitness, define the reasonable placement scheme corresponding to the maximum scheme fitness as the alternative placement scheme.

[0066] When there are at least two reasonable placement schemes with the same maximum scheme fitness, it means that there are multiple reasonable placement schemes that meet the requirements, and further determination of the reasonable placement scheme as the use placement scheme is needed, so the alternative placement scheme is defined to distinguish different reasonable placement schemes for subsequent analysis.

[0067] Step S501: Determine the hole center position in the alternative placement scheme according to the waiting hole region, and determine the shooting separation distance according to the hole center position and the preset detection shooting center.

[0068] The hole center position is a fixed point on the waiting hole region, which can be determined by referring to the product specification parameters after determining the waiting hole region. The detection shooting center is the shooting position point for image acquisition. The shooting separation distance is the distance value between the hole center position and the detection shooting center. The smaller the distance value, the closer the corresponding hole to the detection shooting center, that is, the smaller the possibility of astigmatism, and the better the shooting effect.

[0069] Step S502: Calculate according to all shooting separation distances to determine the effective shooting parameter, and define the alternative placement scheme corresponding to the maximum effective shooting parameter as the use placement scheme.

[0070] The effective shooting parameter is a parameter that reflects whether the image captured by the current image shooting point can better detect each product. The larger the value, the more conducive to product defect detection. The mean value of all shooting separation distances can be calculated and inverted to determine the maximum effective shooting parameter, which reflects that the corresponding alternative placement scheme can better enable the product to be detected, so it can be defined as the use placement scheme.

[0071] After determining the overall detection times, the intelligent detection method for spinning spinneret defects further comprises: Step S600: Determine whether there are at least two effective detection schemes with the same minimum overall detection times.

[0072] The purpose of this judgment is to determine whether there are multiple valid testing solutions that meet the requirements, so as to identify the only valid testing solution to use.

[0073] Step S6001: If there are no at least two valid detection schemes with the same and minimum overall detection count, then the valid detection scheme corresponding to the minimum overall detection count is defined as the detection scheme to be used.

[0074] When there are no at least two valid detection schemes with the same and minimum overall detection count, it means that there is only one valid detection scheme that meets the requirements. In this case, it can be defined as the detection scheme to be used.

[0075] Step S6002: If there are at least two valid detection schemes with the same and minimum overall detection count, the valid detection scheme corresponding to the minimum overall detection count is defined as the alternative detection scheme.

[0076] When there are at least two effective detection schemes with the same and minimum overall detection count, it indicates that there are multiple effective detection schemes that can be used. In this case, they are defined as alternative detection schemes to distinguish between different effective detection schemes and facilitate subsequent analysis.

[0077] Step S601: Count the different valid type combinations on the alternative detection schemes to determine the number of combination types.

[0078] The number of combination types is the number of valid type combinations available in the selected alternative detection schemes.

[0079] Step S602: Calculate the appropriate testing parameters based on the suitability of each valid type combination, the number of type combinations, and the number of combination types in the alternative testing schemes.

[0080] The reasonable testing parameter reflects the feasibility of using the selected testing scheme. A higher value indicates greater feasibility. The calculation formula is as follows: ,in To detect reasonable parameters, For the first The suitability of a combination of effective types. For the first The number of type combinations of a valid type combination For the number of combination types, This is a fixed weight parameter used to adjust the importance of the number of combination types.

[0081] Step S603: Determine the reasonable detection parameter with the largest value according to the sorting rules, and define the alternative detection scheme corresponding to the reasonable detection parameter as the detection scheme to be used.

[0082] The detection reasonable parameter with the largest numerical value can be determined by the sorting rule, that is, the corresponding candidate detection scheme at this time is the most suitable as the use detection scheme, and therefore the use detection scheme can be defined.

[0083] When the use detection scheme is used to detect each spinning jet plate, the intelligent detection method based on spinning jet plate defects further comprises: Step S700: Obtain the historical defect threshold of each detection product type.

[0084] The historical defect threshold is a defect rate threshold that needs to be reached when it is determined that the detection of the spinning jet plate is abnormal. This value can be obtained by recording the hole blockage of the spinning jet plate of a single detection product type during historical detection.

[0085] Step S701: Determine the real-time defect rate according to each detection product type.

[0086] The real-time defect rate is the proportion of spinning jet plates with hole blockage in all spinning jet plates of a single detection product type. In order to reduce the error caused by a small base, the real-time defect rate needs to be calculated and analyzed only when the number of spinning jet plates of a single detection product type is greater than a set base, which is set by the staff according to the actual situation, for example, 5.

[0087] Step S702: Output a detection abnormality signal when the real-time defect rate is greater than the historical defect threshold.

[0088] When the real-time defect rate is greater than the historical defect threshold, it indicates that there may be external interference during the current detection process, which may cause inaccurate detection, that is, there is an abnormality in the detection process. At this time, a detection abnormality signal is outputted to perform alarm processing, so that the management personnel can know the situation in time to intervene.

[0089] Referring to Fig. 2 , based on the same inventive concept, the present application provides an intelligent detection system based on spinning jet plate defects, comprising: An acquisition module is configured to acquire the detection product type and the detection product quantity. A processing module is connected to the acquisition module and is configured to store and process information. The processing module determines the product specification parameter corresponding to the detection product type according to a pre-set type matching relationship. The processing module randomly selects any number of detection product types in each detection product type to form a product type combination, and analyzes and determines the product placement state according to the product specification parameters of the detection product types in the product type combination and the preset detection area, and defines the product type combination whose product placement state is consistent with the preset effective placement state as an effective type combination; The processing module randomly generates the number of type combinations according to each effective type combination, and constructs an overall detection scheme according to the effective type combination and the number of type combinations, and sums up each type combination number in the overall detection scheme to determine the overall detection times; The processing module determines the simulation detection number of each detection product type according to the type combination number and the corresponding effective type combination in the overall detection scheme, and defines the overall detection scheme whose simulation detection number is consistent with the corresponding detection product number as an effective detection scheme; The processing module determines the overall detection times with the smallest numerical value according to the preset sorting rule, and defines the effective detection scheme corresponding to the overall detection times as the use detection scheme, and detects each spinning spinneret according to the use detection scheme; The product type combination construction module is used to reasonably construct the product type combination and reduce the data analysis amount; The product placement state determination module is used to determine the product placement state of the product type combination; The use placement scheme determination module is used to determine the placement of each product in the actual detection process; The reasonable placement scheme screening module is used to screen and process a plurality of reasonable placement schemes that meet the requirements; The effective detection scheme screening module is used to screen and process a plurality of effective detection schemes that meet the requirements; The detection exception condition alarm module is used to alarm the detection exception condition.

[0090] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional modules is exemplified, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

Claims

1. A smart detection method based on defects in spinning spinnerets, characterized in that, include: Obtain the types and quantities of products to be tested; The product specification parameters corresponding to the type of product to be detected are determined based on the preset type matching relationship; Randomly select any number of product types from each product type to form a product type combination, and analyze and determine the product placement status based on the product specification parameters of the product types in the product type combination and the preset testing area. The product type combination whose product placement status is consistent with the preset effective placement status is defined as an effective type combination. The number of type combinations is randomly generated based on each valid type combination, and an overall detection scheme is constructed based on the valid type combinations and the number of type combinations. The overall number of detections is determined by summing the number of each type combination in the overall detection scheme. In the overall testing scheme, the number of simulated tests for each type of product is determined based on the number of type combinations and the corresponding effective type combinations. The overall testing scheme in which the number of simulated tests is consistent with the number of corresponding products is defined as an effective testing scheme. The minimum overall number of tests is determined according to the preset sorting rules, and the effective test scheme corresponding to the minimum overall number of tests is defined as the test scheme to be used. The test scheme is then used to test each spinning spinneret.

2. The intelligent detection method based on spinning spinneret defects according to claim 1, characterized in that, The steps of randomly selecting any number of product types from each product type to form a product type combination include: The coverage area of ​​the hole region is determined according to the product specifications, and the product types are sorted from front to back according to the coverage area of ​​the hole region from largest to smallest to determine the product type order; The first product type to be detected in the product type sequence is defined as the first product type, and the upper limit of the number of first products is determined by calculating based on the hole area coverage of the first product type and the preset detection area. The number of heads is randomly selected within the upper limit, and the area occupied by the heads is calculated based on the number of heads and the corresponding hole area coverage. The detection area is updated based on the detection area and the area occupied by the head, and the head product type is removed from the product type order to update the head product type. Product type combinations are constructed by combining the number of headers corresponding to all tested product types.

3. The intelligent detection method based on spinning spinneret defects according to claim 1, characterized in that, The steps for determining the product placement status based on the product specifications of the tested product type in the product type combination and the preset testing area include: In the product type combination, a virtual center point and virtual placement orientation are randomly generated for each product within the detection area, and the virtual center points and virtual placement orientations of all products are combined to construct a virtual placement scheme; Based on the product specifications, the central virtual point, and the virtual placement orientation in the detection area, a product placement area is simulated and generated, and a waiting hole area is determined in the product placement area. A virtual placement scheme in which all waiting hole areas are within the detection area and there is no overlap of waiting hole areas is defined as a reasonable placement scheme. Determine whether there is at least one reasonable placement scheme for a single product type combination; If there is at least one reasonable placement scheme for a single product type combination, then the effective placement state is determined as the product placement state. If there is no reasonable placement scheme for a single product type combination, the preset invalid placement state will be determined as the product placement state.

4. The intelligent detection method based on spinning spinneret defects according to claim 3, characterized in that, Once a suitable placement scheme is determined, the intelligent detection method based on spinning spinneret defects also includes: The overlapping area of ​​products is determined based on the placement area of ​​each product, and the area of ​​the overlapping area is determined based on the overlapping area of ​​each product. Products with overlapping areas on the product placement area are defined as overlapping products, and the number of overlapping products is determined by counting them. The overall overlapping area is determined by summing the areas of each overlapping region, and the suitability of the scheme is determined by calculating the number of overlaps and the overall overlapping area. The suitability of the scheme with the highest value is determined according to the sorting rules, and the reasonable placement scheme corresponding to the suitability of the scheme is defined as the use placement scheme. When testing each spinning spinneret, each spinning spinneret is placed according to the use placement scheme.

5. The intelligent detection method based on spinning spinneret defects according to claim 4, characterized in that, After determining the suitability of the solution, the intelligent detection method based on spinning spinneret defects also includes: Determine if there exists at least two schemes with the same suitability and the largest reasonable placement scheme; If there are no two solutions with the same suitability and the largest reasonable placement solution, then the reasonable placement solution corresponding to the largest solution suitability is defined as the placement solution to be used. If there are at least two schemes with the same suitability and the largest reasonable placement scheme, then the reasonable placement scheme corresponding to the largest suitability scheme is defined as the alternative placement scheme; In the alternative placement scheme, the center position of the hole is determined according to the waiting hole area, and the shooting interval distance is determined according to the center position of the hole and the preset detection shooting center. The effective shooting parameters are determined by calculating the distance between all shots, and the alternative placement scheme corresponding to the effective shooting parameter with the largest value is defined as the placement scheme to be used.

6. The intelligent detection method based on spinning spinneret defects according to claim 4, characterized in that, At Once the total number of inspections is determined, the intelligent detection method based on spinning spinneret defects also includes: Determine if there are at least two valid detection schemes with the same and minimum overall detection count; If there are no at least two effective detection schemes with the same and minimum overall detection count, then the effective detection scheme corresponding to the minimum overall detection count is defined as the detection scheme to be used. If there are at least two valid detection schemes with the same and minimum overall detection count, then the valid detection scheme with the minimum overall detection count is defined as the alternative detection scheme. The number of combination types is determined by counting different valid combinations of alternative detection schemes. The appropriate testing parameters are determined by calculating the suitability of each effective type combination, the number of type combinations, and the number of combination types among the alternative testing schemes. The maximum reasonable detection parameter is determined according to the sorting rules, and the alternative detection scheme corresponding to the reasonable detection parameter is defined as the detection scheme to be used.

7. The intelligent detection method based on spinning spinneret defects according to claim 1, characterized in that, When using a testing scheme to inspect each spinning spinneret, intelligent detection methods based on spinning spinneret defects also include: Obtain historical defect thresholds for each type of product being tested; Determine the real-time defect rate based on the type of product being tested. When the real-time defect rate exceeds the historical defect threshold, an abnormal detection signal is output.

8. An intelligent detection system based on defects in spinning spinnerets, characterized in that, include: The acquisition module is used to acquire the type and quantity of products to be tested. The processing module, connected to the acquisition module, is used for information storage and processing; The processing module determines the product specification parameters corresponding to the type of product being detected based on a preset type matching relationship; The processing module randomly selects any number of product types from each product type to form a product type combination, and analyzes and determines the product placement status based on the product specification parameters of the product types in the product type combination and the preset detection area. The product type combination whose product placement status is consistent with the preset effective placement status is defined as an effective type combination. The processing module randomly generates the number of type combinations based on each valid type combination, and constructs an overall detection scheme based on the valid type combinations and the number of type combinations. In the overall detection scheme, the summation calculation is performed based on the number of each type combination to determine the overall number of detections. The processing module determines the number of simulated tests for each product type in the overall testing scheme based on the number of type combinations and the corresponding valid type combinations. The overall testing scheme in which the number of simulated tests is consistent with the number of corresponding products is defined as a valid testing scheme. The processing module determines the total number of tests with the smallest value according to the preset sorting rules, defines the effective test scheme corresponding to the total number of tests as the test scheme to be used, and performs tests on each spinning spinneret according to the test scheme to be used.

Images