CN-121998891-A - Solder joint degradation state detection method, device, equipment and storage medium
Abstract
The embodiment of the application relates to the field of defect detection and discloses a welding spot defect detection method, device, equipment and storage medium, comprising the steps of obtaining at least two welding spot images of the same welding spot on a circuit board to be detected, wherein the vertical heights of the welding spot images from the welding spot are different when the welding spot images are shot; the method comprises the steps of fusing all welding spot images to obtain fused images, inputting the fused images into a defect identification model to identify defects, outputting types of the defects and areas where the defects are located, determining form information of the defects based on the areas where the defects are located, and determining degradation states of the welding spots according to the form information of the defects and the types of the defects. The application realizes the detection of the degradation state of the welding spot, improves the accuracy of the assessment of the degradation state of the welding spot, and realizes the effective work of the service life assessment, maintenance and the like of the circuit board.
Inventors
- WANG XU
- WU JIE
- YAO CHONG
- LI YIZHU
- XIAO JIANGLIN
- Kuang fen
- TANG HUAN
- YANG TAO
Assignees
- 中车株洲电力机车研究所有限公司
Dates
- Publication Date
- 20260508
- Application Date
- 20241107
Claims (10)
- 1. A method for detecting a degradation state of a solder joint, comprising: acquiring at least two welding spot images of the same welding spot on a circuit board to be tested, wherein the vertical heights of the welding spot images from the welding spot are different when the welding spot images are shot; fusing the welding spot images to obtain a fused image; inputting the fusion image into a defect identification model to identify defects, and outputting the types of the defects and the areas where the defects are located; determining the form information of the defect based on the region where the defect is located; and determining the degradation state of the welding spot according to the morphological information of the defect and the type of the defect.
- 2. The method of detecting a degradation state of a solder joint according to claim 1, wherein the step of fusing each of the solder joint images to obtain a fused image comprises: Equally dividing each welding spot image to respectively obtain a plurality of original image blocks of each welding spot image; performing discrete cosine transform on each original image block aiming at each welding spot image to obtain a transformed image block; Calculating the focusing degree of each transformation image block, and determining the transformation image block with the largest focusing degree in the same area in each welding spot image as a focusing image block to be selected in the area; And splicing the to-be-selected focusing image blocks of each region to obtain a fusion image of the welding spot.
- 3. The method of claim 1, wherein the weld degradation state comprises at least two of normal, degraded, and failed, each weld degradation state corresponding to a predetermined threshold range, and wherein determining the weld degradation state based on the defect morphology information and the defect classification comprises: calculating a welding spot degradation fraction according to the defect morphology information and the defect type; and determining the welding spot degradation state according to a comparison result of the welding spot degradation fraction and a preset threshold range corresponding to the welding spot degradation state.
- 4. The method of detecting a degraded state of a solder joint according to claim 1, wherein the step of determining morphological information of a defect based on an area where the defect is located includes: and carrying out skeleton extraction on the region where the defect is located to obtain the form information of the defect.
- 5. The solder joint degradation state detection method according to claim 1, wherein the step of acquiring solder joint images of at least two circuit boards to be tested further comprises, before: and determining the position information of the welding spots on the circuit board to be tested.
- 6. The solder joint degradation state detection method according to claim 5, wherein the step of determining the positional information of the solder joint on the circuit board to be tested comprises: acquiring an original image of a circuit board to be tested; Determining a calibration point of the original image and a welding spot position in the original image; and determining the positions of welding spots on the circuit board to be tested in the physical space according to the relative positions of the calibration points of the original image and the welding spot positions in the original image.
- 7. The method for detecting a degradation state of a welding spot according to claim 1, wherein the step of inputting the fused image into a defect recognition model to perform defect recognition and outputting a type of defect and a region where the defect is located further comprises: Dividing the welding spot defects into at least two categories; obtaining a sample welding spot image which comprises welding spot defects and carries out corresponding marking on the categories of the welding spot defects; and constructing an initial defect recognition model based on an example segmentation algorithm, inputting the sample welding spot image into the initial defect recognition model for optimization training, and obtaining the defect recognition model.
- 8. A solder joint defect detection apparatus, comprising: the acquisition module is used for acquiring at least two welding spot images of the same welding spot on the circuit board to be tested, wherein the vertical heights of the welding spot images from the welding spot are different when the welding spot images are shot; The fusion module is used for fusing the welding spot images to obtain a fused image; the defect identification module is used for inputting the fusion image into a defect identification model to carry out defect identification and outputting the type of the defect and the region where the defect is located; The extraction module is used for determining the form information of the defect based on the region where the defect is located; And the detection module is used for determining the degradation state of the welding spot according to the form information of the defect and the type of the defect.
- 9. An electronic device, comprising: At least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the solder joint degradation state detection method according to any one of claims 1 to 7.
- 10. A computer-readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the solder joint degradation state detection method according to any one of claims 1 to 7.
Description
Solder joint degradation state detection method, device, equipment and storage medium Technical Field The embodiment of the invention relates to the technical field of defect detection, in particular to a welding spot defect detection method, device and equipment and a storage medium. Background With the rapid development of electronic packaging technology, the components are miniaturized and integrated more and more, the size of the internal welding spots is smaller, and the number of the internal welding spots is larger. The primary function of the internal solder joints is mechanical support and electrical connection, and once a solder joint breaks, it can cause the entire assembly to fail or fail, with serious consequences. If the degradation state of each welding spot of the board is effectively evaluated in the electronic board overhaul process, the failure rate of the product in field use can be reduced, and meanwhile, the resource waste caused by the early replacement of the product can be avoided, so that the reliability of the electronic board is improved. The traditional welding spot degradation evaluation method such as a manual visual inspection and slicing mode, an electrical parameter and strain parameter test method and the like cannot meet the requirements of nondestructive, high efficiency, high accuracy, unified standard and other maintenance scenes. In recent years, with the development of image recognition and deep learning techniques, the image recognition and deep learning techniques have been gradually applied to a welding spot defect detection apparatus, but such an apparatus mainly recognizes defects at the production stage, and has not been intensively studied for the detection of fine cracks generated by the influence of stress at the use stage. Disclosure of Invention The invention aims to at least provide a welding spot degradation state detection method, a device, equipment and a storage medium, which at least can solve the technical problem that the detection of welding spot defects cannot be accurately realized. To solve the above technical problem, at least one embodiment of the present application provides a method for detecting a degraded state of a solder joint, including: acquiring at least two welding spot images of the same welding spot on a circuit board to be tested, wherein the vertical heights of the welding spot images from the welding spot are different when the welding spot images are shot; fusing the welding spot images to obtain a fused image; inputting the fusion image into a defect identification model to identify defects, and outputting the types of the defects and the areas where the defects are located; determining the form information of the defect based on the region where the defect is located; and determining the degradation state of the welding spot according to the morphological information of the defect and the type of the defect. At least one embodiment of the present application also provides a welding spot degradation state detection apparatus, including: the acquisition module is used for acquiring at least two welding spot images of the same welding spot on the circuit board to be tested, wherein the vertical heights of the welding spot images from the welding spot are different when the welding spot images are shot; The fusion module is used for fusing the welding spot images to obtain a fused image; the defect identification module is used for inputting the fusion image into a defect identification model to carry out defect identification and outputting the type of the defect and the region where the defect is located; The extraction module is used for determining the form information of the defect based on the region where the defect is located; And the detection module is used for determining the degradation state of the welding spot according to the form information of the defect and the type of the defect. At least one embodiment of the application also provides an electronic device comprising at least one processor and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the solder joint degradation state detection method described above. At least one embodiment of the present application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described solder joint degradation state detection method. According to the welding spot degradation state detection method provided by the embodiment of the application, on one hand, fusion is carried out on each welding spot image obtained based on different heights to obtain a fusion image of the welding spots, the definition of the obtained fusion image is high enough, the defects of the welding spots are convenien