Method and system for detecting inductors

Abstract

The application discloses a kind of detection method and system of inductor, define the abnormal part of the inductor at different assembly stages based on the identification of detection image of different assembly stages;Based on a plurality of abnormal parts and the corresponding position of inductor, construct the abnormal set of the inductor, and construct the abnormal distribution map of inductor according to the abnormal set and the factory image of inductor after production is completed;Further, according to the abnormal distribution map of inductor and the production batch of inductor, determine the process to be optimized of the production batch;For the abnormal problem corresponding to the process to be optimized, and output the corresponding optimization strategy for abnormal problem;According to the process to be optimized and the corresponding optimization strategy, output the corresponding optimization report, define the optimization degree of abnormal part in inductor based on each optimization report and the abnormal distribution map of inductor, ensure the accuracy of the optimization degree of abnormal part.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of inductors, and in particular to an inductor detection method and system. BACKGROUND

[0002] With the development of science and technology, inductors are gradually applied in electronic devices. An inductor is assembled from multiple components. In the production process of the inductor, the multiple components are assembled correspondingly and pass through multiple different assembly stages. In each assembly stage, the assembly of the multiple components is not controlled, and it is impossible to know abnormal parts of the inductor in the multiple different assembly stages, so it is impossible to guarantee the detection accuracy and optimization effect of the abnormal parts of the inductor. SUMMARY

[0003] The present application aims to overcome the shortcomings of the prior art. The present application provides an inductor detection method and system. After the production of an inductor is completed, detection images of the inductor in different assembly stages are collected. Abnormal parts of the inductor in different assembly stages are defined based on the recognition of the detection images in different assembly stages. An abnormal set of the inductor is constructed based on multiple abnormal parts and corresponding positions of the inductor, and an abnormal distribution map of the inductor is constructed according to the abnormal set and a factory image of the inductor after the production is completed, so as to control the abnormal set and the factory image in multiple dimensions, thereby overall controlling the abnormal set and the factory image, guaranteeing the accuracy of the abnormal distribution map of the inductor, and further processing the abnormal distribution map of the inductor according to the abnormal distribution map of the inductor.

[0004] Further, a to-be-optimized process of a production batch of the inductor is determined according to the abnormal distribution map of the inductor and the production batch of the inductor. In the to-be-optimized process of the production batch, corresponding abnormal problems are output for the to-be-optimized process, and corresponding optimization strategies are output for the abnormal problems. A corresponding optimization report is output according to the to-be-optimized process and the corresponding optimization strategies. The optimization degree of the abnormal parts in the inductor is defined based on each optimization report and the abnormal distribution map of the inductor. If the optimization degree does not reach a preset optimization program threshold, the to-be-optimized process is further optimized until the optimization degree reaches the preset optimization program threshold, thereby real-time controlling the optimization degree of the abnormal parts in the inductor, and further controlling in multiple dimensions based on each optimization report and the abnormal distribution map of the inductor, thereby guaranteeing the detection accuracy and optimization effect of the abnormal parts of the inductor.

[0005] The embodiment of the present application provides an inductor detection method applied to an inductor detection scene.

[0006] The inductor detection method comprises the following steps.

[0007] After the production of the inductor is completed, detection images of the inductor at different assembly stages are collected;

[0008] Abnormal parts of the inductor at different assembly stages are defined based on recognition of the detection images at different assembly stages;

[0009] An abnormal set of the inductor is constructed based on the abnormal parts and corresponding positions of the inductor, and an abnormal distribution map of the inductor is constructed according to the abnormal set and a delivery image of the inductor after the production is completed;

[0010] A to-be-optimized process of a production batch of the inductor is determined according to the abnormal distribution map of the inductor and the production batch;

[0011] In the to-be-optimized process of the production batch, a corresponding abnormal problem is output for the to-be-optimized process, and a corresponding optimization strategy is output for the abnormal problem;

[0012] A corresponding optimization report is output according to the to-be-optimized process and the corresponding optimization strategy, an optimization degree of abnormal parts in the inductor is defined based on each optimization report and the abnormal distribution map of the inductor, and if the optimization degree does not reach a preset optimization procedure threshold, the to-be-optimized process is further optimized until the optimization degree reaches the preset optimization procedure threshold.

[0013] Optionally, the collection of the detection images of the inductor at different assembly stages after the production of the inductor is completed comprises:

[0014] The production process of the inductor is monitored in real time;

[0015] During the production process of the inductor, a plurality of assembly processes associated with the inductor are determined;

[0016] The inductor is positioned and detected based on detection stations in the plurality of assembly processes;

[0017] During the positioning and detection of the inductor, a plurality of sub-detection images of the inductor in the detection station are collected;

[0018] The detection images of the inductor at the assembly stages are defined based on the plurality of sub-detection images and assembly focuses matched by the assembly processes, at this time, each detection image matches a different assembly stage of the inductor, and the corresponding assembly stage is marked in each detection image;

[0019] Optionally, the definition of the abnormal parts of the inductor at different assembly stages based on recognition of the detection images at different assembly stages comprises:

[0020] The detection images at different assembly stages are determined;

[0021] In each detection image, a corresponding area division mode is matched based on the detection image and the assembly state of the inductor;

[0022] A plurality of detection areas are determined according to the detection image and the corresponding area division mode;

[0023] The plurality of detection areas are associated; a corresponding assembly feature is output based on the synchronous identification of the plurality of detection areas;

[0024] In each detection image, a plurality of assembly features are collected;

[0025] An anomaly detection mode is defined according to the plurality of assembly features and the assembly bias factor of the corresponding assembly stage, and the anomaly part of the inductor in the corresponding assembly stage is defined based on the anomaly detection mode and the plurality of detection areas, and the inductor matches the corresponding anomaly part in different assembly stages.

[0026] Optionally, the anomaly set of the inductor is constructed based on the plurality of anomaly parts and the corresponding positions of the inductor, and the anomaly distribution map of the inductor is constructed according to the anomaly set and the factory image of the inductor after production is completed, including:

[0027] The plurality of anomaly parts are fixed;

[0028] The positions matched by the plurality of anomaly parts are collected and used as the corresponding positions of the inductor;

[0029] The anomaly set of the inductor is constructed based on the plurality of anomaly parts and the corresponding positions of the inductor;

[0030] The factory image of the inductor after production is completed is collected;

[0031] The anomaly set and the factory image of the inductor after production is completed are associated;

[0032] A plurality of anomaly features are output according to the anomaly set, and the plurality of anomaly features are matched to the factory image to construct the anomaly distribution map of the inductor.

[0033] Optionally, the to-be-optimized process of the production batch is determined according to the anomaly distribution map of the inductor and the production batch of the inductor, including:

[0034] The anomaly distribution map of the inductor is fixed;

[0035] Each anomaly part is presented based on the anomaly distribution map of the inductor;

[0036] The relative distance between two adjacent anomaly parts is defined by comparing the positions of the anomaly parts;

[0037] Collect a plurality of relative distances, and construct an anomaly gradient map according to the plurality of relative distances and an anomaly level corresponding to the anomaly part;

[0038] Correlate the anomaly gradient map and the production batch of the inductor;

[0039] Determine a to-be-optimized process of the production batch of the inductor according to the anomaly gradient map and the production batch of the inductor, wherein the production batch of the inductor has a plurality of to-be-optimized processes, and the plurality of to-be-optimized processes correspond to different assembly steps of the inductor.

[0040] Optionally, in the to-be-optimized process of the production batch, a corresponding anomaly problem is output for the to-be-optimized process, and a corresponding optimization strategy is output for the anomaly problem, comprising:

[0041] In the to-be-optimized process of the production batch, a corresponding traversal mode is defined according to each to-be-optimized process and the inductor;

[0042] Each to-be-optimized process and the corresponding traversal mode are traversed;

[0043] A corresponding anomaly assembly action is output based on the traversal of each to-be-optimized process;

[0044] A corresponding anomaly problem is defined according to the detection of the anomaly assembly action.

[0045] Optionally, in the to-be-optimized process of the production batch, a corresponding anomaly problem is output for the to-be-optimized process, and a corresponding optimization strategy is output for the anomaly problem, further comprising:

[0046] Each anomaly problem is framed;

[0047] Each anomaly problem and the corresponding inductor are reversely traced, and a corresponding assembly video is output;

[0048] A plurality of optimization actions are output according to the assembly video and the corresponding anomaly problem;

[0049] A corresponding optimization strategy is output based on the plurality of optimization actions and the production batch of the inductor.

[0050] Optionally, the corresponding optimization report is output according to the to-be-optimized process and the corresponding optimization strategy, the optimization degree of the anomaly part in the inductor is defined based on each optimization report and an anomaly distribution map of the inductor, if the optimization degree does not reach a preset optimization procedure threshold, the to-be-optimized process is further optimized until the optimization degree reaches the preset optimization procedure threshold, comprising:

[0051] The to-be-optimized process and the corresponding optimization strategy are framed;

[0052] The to-be-optimized process and the corresponding optimization strategy are correlated;

[0053] output a corresponding optimization report according to the to-be-optimized process and the corresponding optimization strategy;

[0054] match each optimization report to an abnormal part in the abnormal distribution map of the inductor;

[0055] trigger autonomous optimization of the abnormal part according to each optimization report and the abnormal part.

[0056] Optionally, the output of the corresponding optimization report according to the to-be-optimized process and the corresponding optimization strategy, the definition of the optimization degree of the abnormal part in the inductor based on each optimization report and the abnormal distribution map of the inductor, if the optimization degree does not reach a preset optimization procedure threshold, further optimization for the to-be-optimized process until the optimization degree reaches the preset optimization procedure threshold, further comprises:

[0057] In the autonomous optimization of the abnormal part, the optimization process of the abnormal part is monitored in real time, and the optimization degree of the abnormal part in the inductor is defined;

[0058] If the optimization degree does not reach a preset optimization procedure threshold, further optimization for the to-be-optimized process until the optimization degree reaches the preset optimization procedure threshold.

[0059] In addition, the embodiment of the present application also provides an inductor detection system, the inductor detection system comprises:

[0060] The acquisition module is configured to acquire detection images of the inductor at different assembly stages after production of the inductor is completed;

[0061] The abnormal detection module is configured to define abnormal parts of the inductor at different assembly stages based on recognition of the detection images at different assembly stages;

[0062] The abnormal distribution module is configured to construct an abnormal set of the inductor based on a plurality of abnormal parts and corresponding positions of the inductor, and construct an abnormal distribution map of the inductor according to the abnormal set and a delivery image of the inductor after production is completed;

[0063] The to-be-optimized process detection module is configured to determine a to-be-optimized process of a production batch of the inductor according to the abnormal distribution map of the inductor and the production batch of the inductor;

[0064] The optimization strategy module is configured to output a corresponding abnormal problem for the to-be-optimized process in the to-be-optimized process of the production batch, and output a corresponding optimization strategy for the abnormal problem;

[0065] An optimization degree module is configured to output a corresponding optimization report according to the to-be-optimized process and the corresponding optimization strategy, define an optimization degree of the abnormal part in the inductor based on each optimization report and the abnormal distribution map of the inductor, and further optimize the to-be-optimized process until the optimization degree reaches the preset optimization procedure threshold if the optimization degree fails to reach the preset optimization procedure threshold.

[0066] In the embodiment of the present application, after the production of the inductor is completed, the detection images of the inductor at different assembly stages are collected, the abnormal parts of the inductor at different assembly stages are defined based on the recognition of the detection images at different assembly stages, the abnormal set of the inductor is constructed based on the plurality of abnormal parts and the corresponding positions of the inductor, and the abnormal distribution map of the inductor is constructed according to the abnormal set and the factory image of the inductor after the production is completed, so as to control the abnormal set and the factory image in multiple dimensions, thereby overall controlling the abnormal set and the factory image, ensuring the accuracy of the abnormal distribution map of the inductor, and presenting the abnormal parts of the inductor at each assembly process according to the abnormal distribution map of the inductor, so as to further process the abnormal distribution map of the inductor.

[0067] Further, the to-be-optimized process of the production batch is determined according to the abnormal distribution map of the inductor and the production batch of the inductor, the corresponding abnormal problem is output for the to-be-optimized process in the production batch, the corresponding optimization strategy is output for the abnormal problem, the corresponding optimization report is output according to the to-be-optimized process and the corresponding optimization strategy, the optimization degree of the abnormal part in the inductor is defined based on each optimization report and the abnormal distribution map of the inductor, and the to-be-optimized process is further optimized until the optimization degree reaches the preset optimization procedure threshold if the optimization degree fails to reach the preset optimization procedure threshold, so as to control the optimization degree of the abnormal part in the inductor in real time, and further control in multiple dimensions based on each optimization report and the abnormal distribution map of the inductor, thereby ensuring the detection accuracy of the abnormal part of the inductor and the optimization effect. BRIEF DESCRIPTION OF DRAWINGS

[0068] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0069] Figure 1 is a flowchart of the detection method of the inductor in the embodiment of the present application;

[0070] Figure 2is a flowchart of S11 in the detection method of the inductor in the embodiment of the application;

[0071] Figure 3 is a flowchart of S12 in the detection method of the inductor in the embodiment of the application;

[0072] Figure 4 is a flowchart of S13 in the detection method of the inductor in the embodiment of the application;

[0073] Figure 5 is a flowchart of S14 in the detection method of the inductor in the embodiment of the application;

[0074] Figure 6 is a flowchart of S15 in the detection method of the inductor in the embodiment of the application;

[0075] Figure 7 is a flowchart of S16 in the detection method of the inductor in the embodiment of the application;

[0076] Figure 8 is a structural composition diagram of the detection system of the inductor in the embodiment of the application;

[0077] Figure 9 is a hardware diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0078] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the application.

[0079] Please refer to Figures 1 to 9 A detection method of an inductor is applied to a detection scenario of the inductor. The detection method of the inductor comprises the following steps.

[0080] Step S11: After the production of the inductor is completed, detection images of the inductor at different assembly stages are collected.

[0081] Step S12: Abnormal parts of the inductor at different assembly stages are defined based on the recognition of the detection images at different assembly stages.

[0082] Step S13: An abnormal set of the inductor is constructed based on the multiple abnormal parts and corresponding positions of the inductor, and an abnormal distribution diagram of the inductor is constructed according to the abnormal set and a factory image of the inductor after the production is completed.

[0083] Step S14: determining a to-be-optimized process of the production batch according to the abnormal distribution map of the inductor and the production batch of the inductor;

[0084] Step S15: outputting a corresponding abnormal problem for the to-be-optimized process and outputting a corresponding optimization strategy for the abnormal problem in the to-be-optimized process of the production batch;

[0085] Step S16: outputting a corresponding optimization report according to the to-be-optimized process and the corresponding optimization strategy, defining an optimization degree of the abnormal part in the inductor based on each optimization report and the abnormal distribution map of the inductor, and further optimizing the to-be-optimized process until the optimization degree reaches a preset optimization procedure threshold if the optimization degree does not reach the preset optimization procedure threshold.

[0086] In the embodiment of the present application, after the production of the inductor is completed, detection images of the inductor at different assembly stages are collected; abnormal parts of the inductor at different assembly stages are defined based on recognition of the detection images at different assembly stages; an abnormal set of the inductor is constructed based on a plurality of abnormal parts and corresponding positions of the inductor, and an abnormal distribution map of the inductor is constructed according to the abnormal set and a factory image of the inductor after production is completed, so as to control the abnormal set and the factory image in multiple dimensions, thereby overall controlling the abnormal set and the factory image, ensuring the accuracy of the abnormal distribution map of the inductor, and presenting abnormal parts of the inductor in each assembly process according to the abnormal distribution map of the inductor, so as to further process the abnormal distribution map of the inductor.

[0087] Further, a to-be-optimized process of the production batch is determined according to the abnormal distribution map of the inductor and the production batch of the inductor; a corresponding abnormal problem is output for the to-be-optimized process, and a corresponding optimization strategy is output for the abnormal problem in the to-be-optimized process; a corresponding optimization report is output according to the to-be-optimized process and the corresponding optimization strategy, an optimization degree of the abnormal part in the inductor is defined based on each optimization report and the abnormal distribution map of the inductor, and the to-be-optimized process is further optimized until the optimization degree reaches a preset optimization procedure threshold if the optimization degree does not reach the preset optimization procedure threshold, so as to control the optimization degree of the abnormal part in the inductor in real time, and further control in multiple dimensions based on each optimization report and the abnormal distribution map of the inductor, thereby ensuring the detection accuracy of the abnormal part of the inductor and the optimization effect.

[0088] Reference Figure 2 In step S11, after the production of the inductor is completed, detection images of the inductor at different assembly stages are collected;

[0089] In the implementation of the present application, the specific steps can be:

[0090] S111: Real-time monitoring of the production process of the inductor;

[0091] S112: In the production process of the inductor, the multiple assembly processes associated with the inductor are defined;

[0092] S113: Based on the detection station in the multiple assembly processes, the inductor is positioned and detected;

[0093] S114: In the positioning and detection of the inductor, multiple sub-detection images of the inductor in the detection station are collected;

[0094] S115: Based on the multiple sub-detection images and the assembly focus matched by the assembly process, the detection image of the inductor in the assembly stage is defined, at this time, each detection image matches a different assembly stage of the inductor, and the corresponding assembly stage is marked in each detection image.

[0095] In the embodiment of the present application, the production process of the inductor is monitored in real time, and the production process of the inductor is further controlled, at this time, in the production process of the inductor, the multiple assembly processes associated with the inductor are defined, so as to control the multiple assembly processes associated with the inductor, so as to introduce the multiple assembly processes associated with the inductor, and based on the detection station in the multiple assembly processes, the inductor is positioned and detected.

[0096] Therefore, in the positioning and detection of the inductor, multiple sub-detection images of the inductor in the detection station are collected, so as to control the multiple sub-detection images, and based on the multiple sub-detection images and the assembly focus matched by the assembly process, the detection image of the inductor in the assembly stage is defined, based on the multiple sub-detection images and the assembly focus matched by the assembly process, multiple dimensions are controlled, and then the detection image of the inductor in the assembly stage is defined, at this time, each detection image matches a different assembly stage of the inductor, and the corresponding assembly stage is marked in each detection image.

[0097] Reference Figure 3 In step S12, based on the identification of the detection images of different assembly stages, the abnormal part of the inductor in different assembly stages is defined;

[0098] In the implementation of the present application, the specific steps can be:

[0099] S121: Define the detection image of different assembly stages;

[0100] S122: In each detection image, based on the detection image and the assembly state of the inductor, the corresponding area division mode is matched;

[0101] S123: determining a plurality of detection regions according to the detection image and the corresponding region division mode;

[0102] S124: associating the plurality of detection regions; and outputting the corresponding assembly features based on synchronous identification of the plurality of detection regions;

[0103] S125: collecting a plurality of assembly features in each detection image;

[0104] S126: defining an abnormality detection mode according to the plurality of assembly features and an assembly bias factor of the corresponding assembly stage, and defining an abnormal part of the inductor in the corresponding assembly stage based on the abnormality detection mode and the plurality of detection regions, so that the inductor matches the corresponding abnormal part in different assembly stages.

[0105] In the embodiments of the present application, the detection images of different assembly stages are framed, so that the corresponding detection images are matched for different assembly stages, thereby performing targeted control on the detection images for further processing of each detection image.

[0106] At this time, in each detection image, the corresponding region division mode is matched based on the detection image and the assembly state of the inductor, which is compatible with the overall consideration of the detection image and the assembly state of the inductor, and performs multi-dimensional control on the detection image and the assembly state of the inductor, so as to output the corresponding region division mode. The region division mode can be an overall region division mode, a partial region division mode, and a targeted region division mode.

[0107] Further, a plurality of detection regions are determined according to the detection image and the corresponding region division mode, which introduces the detection image and the corresponding region division mode, and performs overall consideration on the detection image and the corresponding region division mode, thereby determining a plurality of detection regions, which realizes the segmentation of the detection image into a plurality of detection regions, and ensures the accurate control of the plurality of detection regions.

[0108] Therefore, the plurality of detection regions are associated; and the corresponding assembly features are output based on synchronous identification of the plurality of detection regions, so as to perform synchronous identification on the plurality of detection regions and output a plurality of assembly features in the process of synchronous identification.

[0109] At this time, in each detection image, a plurality of assembly features are collected; an abnormality detection mode is defined according to the plurality of assembly features and an assembly bias factor of the corresponding assembly stage, and an abnormal part of the inductor in the corresponding assembly stage is defined based on the abnormality detection mode and the plurality of detection regions, so as to further control the abnormal part, and the inductor matches the corresponding abnormal part in different assembly stages.

[0110] Reference Figure 4In step S13, an anomaly set of the inductor is constructed based on the plurality of anomaly parts and the corresponding positions of the inductor, and an anomaly distribution map of the inductor is constructed according to the anomaly set and a factory image of the inductor after production is completed;

[0111] In the implementation of the present application, the specific steps can be:

[0112] S131: freeze a plurality of anomaly parts;

[0113] S132: collect positions matched by the plurality of anomaly parts as corresponding positions of the inductor;

[0114] S133: construct an anomaly set of the inductor based on the plurality of anomaly parts and the corresponding positions of the inductor;

[0115] S134: collect a factory image of the inductor after production is completed;

[0116] S135: correlate the anomaly set and the factory image of the inductor after production is completed;

[0117] S136: output a plurality of anomaly features according to the anomaly set, and match the plurality of anomaly features to the factory image to construct an anomaly distribution map of the inductor.

[0118] In the embodiment of the present application, after the production of the inductor is completed, detection images of the inductor at different assembly stages are collected; anomaly parts of the inductor at different assembly stages are defined based on recognition of the detection images at different assembly stages; an anomaly set of the inductor is constructed based on the plurality of anomaly parts and the corresponding positions of the inductor, and an anomaly distribution map of the inductor is constructed according to the anomaly set and a factory image of the inductor after production is completed, so as to control the anomaly set and the factory image in multiple dimensions, thereby overall controlling the anomaly set and the factory image, ensuring the accuracy of the anomaly distribution map of the inductor, and at the same time, presenting the anomaly parts of the inductor at each assembly process according to the anomaly distribution map of the inductor, so as to further process the anomaly distribution map of the inductor.

[0119] At this time, a plurality of anomaly parts are frozen, and the plurality of anomaly parts are further controlled, so as to collect positions matched by the plurality of anomaly parts as corresponding positions of the inductor, thereby determining the plurality of anomaly parts and the corresponding positions of the inductor, and correlating the plurality of anomaly parts and the corresponding positions of the inductor, so as to construct an anomaly set of the inductor based on the plurality of anomaly parts and the corresponding positions of the inductor.

[0120] Further, a factory image of the inductor after production is completed is collected, the factory image is framed, and the abnormality set and the factory image of the inductor after production are associated, the abnormality set and the factory image of the inductor after production are considered as a whole, and then a plurality of abnormal features are output according to the abnormality set, the plurality of abnormal features are matched to the factory image, and an abnormal distribution map of the inductor is constructed, which presents the position of the inductor and the plurality of abnormal features relative to the inductor.

[0121] Reference Figure 5 , S14: determining a to-be-optimized process of the production batch of the inductor according to the abnormal distribution map of the inductor and the production batch of the inductor;

[0122] In the specific implementation of the present application, the specific steps can be:

[0123] S141: framing the abnormal distribution map of the inductor;

[0124] S142: presenting each abnormal part based on the abnormal distribution map of the inductor;

[0125] S143: comparing the positions of each abnormal part and defining the relative distance between two adjacent abnormal parts;

[0126] S144: collecting a plurality of relative distances and constructing an abnormal gradient map according to the plurality of relative distances and the abnormal grades corresponding to the abnormal parts;

[0127] S145: associating the abnormal gradient map and the production batch of the inductor;

[0128] S146: determining a to-be-optimized process of the production batch of the inductor according to the abnormal gradient map and the production batch of the inductor, wherein the production batch of the inductor has a plurality of to-be-optimized processes, and the plurality of to-be-optimized processes correspond to different assembly steps of the inductor.

[0129] In the embodiments of the present application, the abnormal distribution map of the inductor is framed, and the abnormal distribution map of the inductor is further controlled, so as to present each abnormal part based on the abnormal distribution map of the inductor, and each abnormal part is further processed.

[0130] At this time, the positions of each abnormal part are compared, the relative distance between two adjacent abnormal parts is defined, a plurality of relative distances are collected, and an abnormal gradient map is constructed according to the plurality of relative distances and the abnormal grades corresponding to the abnormal parts, the plurality of relative distances and the abnormal grades corresponding to the abnormal parts are controlled as a whole, so as to ensure the accuracy of the abnormal gradient map.

[0131] Therefore, the abnormal gradient graph and the production batch of the inductor are associated; the to-be-optimized process of the production batch is determined according to the abnormal gradient graph and the production batch of the inductor, multi-dimensional control is performed according to the abnormal gradient graph and the production batch of the inductor, and the abnormal part presented by the abnormal gradient graph and the production batch of the inductor are fully utilized, so that the accuracy of the to-be-optimized process of the production batch is ensured. At this time, the production batch of the inductor has multiple to-be-optimized processes, and the multiple to-be-optimized processes correspond to different assembly steps of the inductor.

[0132] Reference Figure 6 , S15: In the to-be-optimized process of the production batch, the corresponding abnormal problem is output for the to-be-optimized process, and the corresponding optimization strategy is output for the abnormal problem;

[0133] In the specific implementation process of the application, the specific steps can be:

[0134] S151: In the to-be-optimized process of the production batch, a corresponding traversal mode is defined according to each to-be-optimized process and the inductor;

[0135] S152: Each to-be-optimized process and the corresponding traversal mode are traversed;

[0136] S153: The corresponding abnormal assembly action is output based on the traversal of each to-be-optimized process;

[0137] S154: The corresponding abnormal problem is defined according to the detection of the abnormal assembly action;

[0138] S155: Each abnormal problem is defined; the corresponding assembly video is output according to each abnormal problem and the inductor;

[0139] S156: Multiple optimization actions are output according to the assembly video and the corresponding abnormal problem;

[0140] S157: The corresponding optimization strategy is output based on the multiple optimization actions and the production batch of the inductor.

[0141] In the embodiment of the application, in the to-be-optimized process of the production batch, a corresponding traversal mode is defined according to each to-be-optimized process and the inductor, so that the traversal mode is introduced and targeted traversal is performed according to the traversal mode.

[0142] At this time, each to-be-optimized process and the corresponding traversal mode are traversed, so that targeted traversal is performed on each to-be-optimized process, the corresponding abnormal assembly action is output based on the traversal of each to-be-optimized process, the abnormal assembly action is introduced, and further control is performed on the abnormal assembly action, so that the corresponding abnormal problem is defined according to the detection of the abnormal assembly action.

[0143] Therefore, the abnormal problems are fixed, the corresponding assembly videos are output according to the abnormal problems and the corresponding inductors, the optimization actions are output according to the assembly videos and the abnormal problems, the optimization strategies are output based on the optimization actions and the production batches of the inductors, so that the optimization strategies are further processed, and the rationality of the optimization strategies is ensured.

[0144] Reference Figure 7 S16: An optimization report is output according to the to-be-optimized process and the corresponding optimization strategy, the optimization degree of the abnormal part in the inductor is defined based on the optimization reports and the abnormal distribution diagram of the inductor, if the optimization degree does not reach a preset optimization program threshold, the to-be-optimized process is further optimized until the optimization degree reaches the preset optimization program threshold.

[0145] In the specific implementation process of the present application, the specific steps can be:

[0146] S161: The to-be-optimized process and the corresponding optimization strategy are fixed.

[0147] S162: The to-be-optimized process and the corresponding optimization strategy are associated.

[0148] S163: An optimization report is output according to the to-be-optimized process and the corresponding optimization strategy.

[0149] S164: Each optimization report is matched to an abnormal part in the abnormal distribution diagram of the inductor.

[0150] S165: The autonomous optimization of the abnormal part is triggered according to the optimization reports and the abnormal part.

[0151] S166: In the autonomous optimization of the abnormal part, the optimization process of the abnormal part is monitored in real time, and the optimization degree of the abnormal part in the inductor is defined.

[0152] S167: If the optimization degree does not reach a preset optimization program threshold, the to-be-optimized process is further optimized until the optimization degree reaches the preset optimization program threshold.

[0153] In the implementation of the present application, the abnormality distribution of the inductor and the production batch of the inductor are used to determine the process to be optimized in the production batch; in the process to be optimized in the production batch, the corresponding abnormality problem is output for the process to be optimized, and the corresponding optimization strategy is output for the abnormality problem; the corresponding optimization report is output according to the process to be optimized and the corresponding optimization strategy, the optimization degree of the abnormal part in the inductor is defined based on each optimization report and the abnormality distribution of the inductor, if the optimization degree does not reach the preset optimization procedure threshold, the process to be optimized is further optimized until the optimization degree reaches the preset optimization procedure threshold, so as to control the optimization degree of the abnormal part in the inductor in real time, and then control in multiple dimensions based on each optimization report and the abnormality distribution of the inductor, so as to ensure the detection accuracy and optimization effect of the abnormal part of the inductor.

[0154] At this time, the process to be optimized and the corresponding optimization strategy are fixed and associated, so as to output the corresponding optimization report according to the process to be optimized and the corresponding optimization strategy, so as to present the corresponding optimization report and the corresponding optimization action in the optimization report.

[0155] Further, each optimization report is matched to the abnormal part in the abnormality distribution of the inductor, so as to associate the abnormal part and the corresponding optimization report, and further control the abnormal part, so as to trigger the autonomous optimization of the abnormal part according to each optimization report and the abnormal part;

[0156] Therefore, in the autonomous optimization of the abnormal part, the optimization process of the abnormal part is monitored in real time, and the optimization degree of the abnormal part in the inductor is defined; if the optimization degree does not reach the preset optimization procedure threshold, the process to be optimized is further optimized until the optimization degree reaches the preset optimization procedure threshold, so as to control the optimization degree of the abnormal part in the inductor in real time, and then control in multiple dimensions based on each optimization report and the abnormality distribution of the inductor, so as to ensure the detection accuracy and optimization effect of the abnormal part of the inductor.

[0157] In the embodiment of the present application, through the method in the embodiment of the present application, after the production of the inductor is completed, detection images of the inductor at different assembly stages are collected; abnormal parts of the inductor at different assembly stages are defined based on recognition of the detection images at different assembly stages; an abnormal set of the inductor is constructed based on a plurality of abnormal parts and corresponding positions of the inductor, and an abnormal distribution map of the inductor is constructed according to the abnormal set and a factory image of the inductor after the production is completed, so as to control in multiple dimensions for the abnormal set and the factory image, thereby overall controlling the abnormal set and the factory image, ensuring the accuracy of the abnormal distribution map of the inductor, and at the same time, the abnormal parts of the inductor in each assembly process are presented according to the abnormal distribution map of the inductor, so as to further process the abnormal distribution map of the inductor.

[0158] Further, the abnormal distribution map of the inductor and the production batch of the inductor are used to determine a to-be-optimized process of the production batch; in the to-be-optimized process of the production batch, corresponding abnormal problems are output for the to-be-optimized process, and corresponding optimization strategies are output for the abnormal problems; a corresponding optimization report is output according to the to-be-optimized process and the corresponding optimization strategies, the optimization degree of the abnormal parts in the inductor is defined based on each optimization report and the abnormal distribution map of the inductor, if the optimization degree does not reach a preset optimization procedure threshold, the to-be-optimized process is further optimized until the optimization degree reaches the preset optimization procedure threshold, so as to control the optimization degree of the abnormal parts in the inductor in real time, and further control in multiple dimensions based on each optimization report and the abnormal distribution map of the inductor, thereby ensuring the detection accuracy and optimization effect of the abnormal parts of the inductor.

[0159] Please refer to Figure 8 , Figure 8 is a structural composition schematic diagram of the detection system of the inductor in the embodiment of the present application.

[0160] As Figure 8 indicated, a detection system of an inductor comprises:

[0161] The acquisition module 21 is configured to collect detection images of the inductor at different assembly stages after the production of the inductor is completed.

[0162] The abnormal detection module 22 is configured to define abnormal parts of the inductor at different assembly stages based on recognition of the detection images at different assembly stages.

[0163] The abnormal distribution module 23 is configured to construct an abnormal set of the inductor based on a plurality of abnormal parts and corresponding positions of the inductor, and construct an abnormal distribution map of the inductor according to the abnormal set and a factory image of the inductor after the production is completed.

[0164] The to-be-optimized process detection module 24 is configured to determine a to-be-optimized process of a production batch of the inductor according to the abnormality distribution diagram of the inductor and the production batch of the inductor.

[0165] The optimization strategy module 25 is configured to output a corresponding abnormality problem for the to-be-optimized process and output a corresponding optimization strategy for the abnormality problem in the to-be-optimized process of the production batch of the inductor.

[0166] The optimization degree module 26 is configured to output a corresponding optimization report according to the to-be-optimized process and the corresponding optimization strategy, define an optimization degree of an abnormal part in the inductor based on each optimization report and the abnormality distribution diagram of the inductor, and further optimize the to-be-optimized process until the optimization degree reaches a preset optimization procedure threshold if the optimization degree does not reach the preset optimization procedure threshold.

[0167] Referring to Figure 9 , the electronic device 40 according to this embodiment of the present application will be described below with reference to Figure 9 . Figure 9 The electronic device 40 shown is merely an example and should not be taken as limiting the functionality or the applicability of embodiments of the present application.

[0168] As shown in Figure 9 , the electronic device 40 is in the form of a general computing device. The components of the electronic device 40 can include, but are not limited to, the at least one processing unit 41 described above, the at least one storage unit 42 described above, and a bus 43 connecting different system components, including the storage unit 42 and the processing unit 41.

[0169] The storage unit stores program codes which can be executed by the processing unit 41, so that the processing unit 41 performs the steps according to various exemplary embodiments of the present application described in the "Embodiment Method" part of the present specification.

[0170] The storage unit 42 can include a readable medium in the form of a volatile storage unit, such as a random access memory (RAM) 421 and / or a cache memory 422, and can further include a read-only memory (ROM) 423.

[0171] The storage unit 42 can further include program / utility 424 having a set of at least one program modules 425, including but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which can include implementation of a network environment or some combination thereof.

[0172] Bus 43 can be one of several types of bus structures including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or local bus using any of a variety of bus structures, and the like.

[0173] Electronic device 40 can also communicate with one or more external devices such as a keyboard or a pointing device, a Bluetooth device, etc., and can also communicate with one or more devices that enable a user to interact with electronic device 40 and / or one or more devices that enable electronic device 40 to communicate with one or more other computing devices. Such communication can occur via input / output (I / O) interface 44. Still yet, electronic device 40 can communicate with one or more networks such as a local area network (LAN), a general wide area network (WAN), and / or a public network such as the Internet, via network adapter 45. As depicted, network adapter 45 communicates with the other components of electronic device 40 via bus 43. It should be appreciated that although not shown, other hardware and / or software modules could be used in conjunction with electronic device 40. Such as, but not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival Figure 9 systems, etc. Figure 9 It should be appreciated that the software modules described herein can be implemented in hardware and / or software (including firmware, resident software, micro-code, etc.) and can take any number of physical forms including, but not limited to, a modem, a personal computer, a network card, an application-specific integrated circuit (ASIC), etc. Furthermore, the software modules can be stored in any type of non- transitory computer-readable medium or media (e.g., random access memory (RAM), read only memory (ROM), magnetic disk, optical disk, etc.) associated with the electronic device 40, either on a "take away" basis, or as a self-contained hardware component with the various software modules integrated therewith. Accordingly, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-transitory computer-readable medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.) or a network, and includes a plurality of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to perform the methods according to the embodiments of the present disclosure.

[0174] From the above description of the embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-transitory computer-readable medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.) or a network, and includes a plurality of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to perform the methods according to the embodiments of the present disclosure.

[0175] Those skilled in the art can understand that all or part of the steps of the above-mentioned embodiments can be completed by a program instructing the relevant hardware, and the program can be stored in a computer-readable storage medium, which can include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc. Moreover, the computer program instructions stored therein can enable the computer to perform the methods according to the above-mentioned embodiments when the computer program instructions are executed by the computer.

[0176] In addition, the detection method and system of the inductor provided by the embodiment of the present application are described in detail, the principle and implementation manner of the present application are described by using specific examples in this paper, and the above embodiment is only used to help understand the method of the present application and the core idea; at the same time, for the general technical personnel in the art, according to the idea of the present application, the specific implementation manner and application range will be changed, and the above description should not be understood as the limitation of the present application.

Claims

1. A method for detecting an inductor, characterized in that, Applications include inductor testing. The inductor detection method includes: After the inductor is manufactured, inspection images of the inductor are collected at different assembly stages; The abnormal parts of the inductor at different assembly stages are defined based on the recognition of detection images at different assembly stages; An anomaly set for the inductor is constructed based on multiple abnormal parts and their corresponding locations. An anomaly distribution map of the inductor is then constructed based on this anomaly set and the factory images of the inductor after production is completed. Based on the anomaly distribution map of the inductor and the production batch of the inductor, the optimization process for this production batch is determined as follows: The anomaly distribution map of the inductor is fixed; each anomaly is presented based on the anomaly distribution map; the positions of each anomaly are compared, and the relative distance between two adjacent anomaly parts is defined; multiple relative distances are collected, and an anomaly gradient map is constructed based on the multiple relative distances and the anomaly level corresponding to the anomaly part; the anomaly gradient map is correlated with the production batch of the inductor; the optimization process for this production batch is determined based on the anomaly gradient map and the production batch of the inductor. At this point, there are multiple optimization processes for the inductor production batch, and these multiple optimization processes correspond to different assembly steps of the inductor. In the processes to be optimized in this production batch, corresponding anomalies are output for each process, and corresponding optimization strategies are output for each anomaly. This includes: defining corresponding traversal patterns for each process and inductor in the processes to be optimized; traversing each process and its corresponding traversal pattern; outputting corresponding abnormal assembly actions based on the traversal of each process; defining corresponding anomalies based on the detection of abnormal assembly actions; freezing each anomaly; performing reverse tracing based on each anomaly and its corresponding inductor, and outputting corresponding assembly videos; outputting multiple optimization actions based on the assembly videos and corresponding anomalies; and outputting corresponding optimization strategies based on the multiple optimization actions and the production batch of inductors. Based on the process to be optimized and the corresponding optimization strategy, an optimization report is output. Based on each optimization report and the inductor anomaly distribution map, the optimization degree of the abnormal part in the inductor is defined. If the optimization degree does not reach the preset optimization program threshold, the process to be optimized is further optimized until the optimization degree reaches the preset optimization program threshold.

2. The inductor detection method according to claim 1, characterized in that, After the inductor is manufactured, inspection images of the inductor are collected at different assembly stages, including: Real-time monitoring of the inductor manufacturing process; In the production process of inductors, several assembly steps associated with inductors are fixed; Positioning and testing of inductors are performed based on testing stations in multiple assembly processes; In the positioning and detection of inductors, multiple sub-detection images of the inductor at this detection station are acquired. Based on multiple sub-detection images and the assembly focus matched by the assembly process, the detection images of the inductor at this assembly stage are defined. At this time, each detection image matches a different assembly stage of the inductor, and the corresponding assembly stage is marked on each detection image.

3. The inductor detection method according to claim 2, characterized in that, The definition of abnormal parts of the inductor at different assembly stages based on the identification of detection images at different assembly stages includes: Freeze-frame detection images at different assembly stages; In each detection image, a corresponding region segmentation pattern is matched based on the detection image and the assembly state of the inductor. Multiple detection regions are determined based on the detected image and the corresponding region segmentation pattern; Associate multiple detection regions; output corresponding assembled features based on the synchronous identification of multiple detection regions; Multiple assembled features are collected from each detected image; An anomaly detection method is defined based on multiple assembly characteristics and the assembly emphasis factors of the corresponding assembly stages. Based on this anomaly detection method and multiple detection areas, the abnormal part of the inductor in the corresponding assembly stage is defined. At the same time, the inductor is matched with the corresponding abnormal part in different assembly stages.

4. The inductor detection method according to claim 3, characterized in that, The process involves constructing an anomaly set for the inductor based on multiple abnormal parts and their corresponding locations, and then constructing an anomaly distribution map for the inductor based on this anomaly set and factory images of the inductor after production is completed. This includes: Freeze multiple abnormal parts; Collect the locations matched by multiple abnormal parts and use them as the corresponding locations of the inductor; The anomaly set of the inductor is constructed based on multiple abnormal parts and the corresponding positions of the inductor. Collect factory images of the inductors after production is completed; Associate this set of anomalies with factory images of the inductors after production is complete; Based on the set of anomalies, multiple anomaly features are output and matched with the factory images to construct an anomaly distribution map of the inductor.

5. The inductor detection method according to claim 1, characterized in that, The process outputs an optimization report based on the process to be optimized and the corresponding optimization strategy. The optimization level of the abnormal parts in the inductor is defined based on each optimization report and the inductor's anomaly distribution diagram. If the optimization level does not reach a preset optimization threshold, further optimization is performed on the process to be optimized until the optimization level reaches the preset optimization threshold, including: Define the process to be optimized and the corresponding optimization strategy. Associate the process to be optimized with the corresponding optimization strategy; Based on the process to be optimized and the corresponding optimization strategy, output the corresponding optimization report; Match each optimization report to the abnormal portion of the inductor's anomaly distribution diagram; Based on various optimization reports and the abnormal parts, the abnormal parts are triggered to perform autonomous optimization.

6. The inductor detection method according to claim 5, characterized in that, The process of outputting an optimization report based on the process to be optimized and the corresponding optimization strategy, defining the optimization degree of the abnormal parts in the inductor based on each optimization report and the anomaly distribution map of the inductor, and further optimizing the process to be optimized if the optimization degree does not reach the preset optimization program threshold until the optimization degree reaches the preset optimization program threshold, also includes: In the autonomous optimization of the abnormal part, the optimization process of the abnormal part is monitored in real time, and the degree of optimization of the abnormal part in the inductor is defined. If the optimization level does not reach the preset optimization program threshold, the process to be optimized will be further optimized until the optimization level reaches the preset optimization program threshold.

7. A detection system for an inductor, characterized in that, The inductor detection system is applied to the inductor detection method as described in any one of claims 1-6, and the inductor detection system comprises: The acquisition module is used to acquire inspection images of the inductor at different assembly stages after the inductor is manufactured. An anomaly detection module is used to define the abnormal parts of the inductor at different assembly stages based on the recognition of detection images at different assembly stages. The anomaly distribution module is used to construct an anomaly set for the inductor based on multiple anomalies and their corresponding locations, and to construct an anomaly distribution map for the inductor based on the anomaly set and the factory image of the inductor after production is completed. The process to be optimized detection module is used to determine the processes to be optimized for a production batch based on the inductor's anomaly distribution map and the production batch of the inductor: freezing the anomaly distribution map of the inductor; presenting each anomaly based on the anomaly distribution map; comparing the positions of each anomaly and defining the relative distance between two adjacent anomalies; collecting multiple relative distances and constructing an anomaly gradient map based on the multiple relative distances and the anomaly level corresponding to the anomaly; associating the anomaly gradient map with the inductor's production batch; and determining the processes to be optimized for that production batch based on the anomaly gradient map and the inductor's production batch. At this point, there are multiple processes to be optimized in the inductor's production batch, and these multiple processes correspond to different assembly steps of the inductor. The optimization strategy module is used to output corresponding anomalies for the processes to be optimized in the production batch, and to output corresponding optimization strategies for the anomalies. This includes: defining corresponding traversal patterns for each process to be optimized and the inductors in the production batch; traversing each process to be optimized and its corresponding traversal pattern; outputting corresponding abnormal assembly actions based on the traversal of each process to be optimized; defining corresponding anomalies based on the detection of abnormal assembly actions; freezing each anomaly; performing reverse tracing based on each anomaly and its corresponding inductor, and outputting corresponding assembly videos; outputting multiple optimization actions based on the assembly videos and corresponding anomalies; and outputting corresponding optimization strategies based on the multiple optimization actions and the production batch of inductors. The optimization level module is used to output the corresponding optimization report based on the process to be optimized and the corresponding optimization strategy. Based on each optimization report and the abnormal distribution map of the inductor, the optimization level of the abnormal part in the inductor is defined. If the optimization level does not reach the preset optimization program threshold, the process to be optimized is further optimized until the optimization level reaches the preset optimization program threshold.

Images