CN-121998947-A - PCBA production line intelligent monitoring and closed-loop control system based on Internet of things sensing and data driving

CN121998947ACN 121998947 ACN121998947 ACN 121998947ACN-121998947-A

Abstract

The invention discloses an intelligent PCBA production line monitoring and closed-loop control system based on Internet of things sensing and data driving, which comprises a control terminal, wherein the control terminal is configured to receive an image comprising a printed circuit board assembly, determine whether the image comprises an edge identification mark or not, command an image acquisition device to adjust the position and re-shoot the image comprising the printed circuit board assembly if the image does not comprise the edge identification mark, determine whether the image has a correct scaling ratio based on the edge identification mark if the image comprises the edge identification mark, and continuously analyze the image if the image has the correct scaling ratio. The invention can improve the stability and accuracy of image detection, realize the differential parameter adjustment of the subarea, enhance the defect tracing and process optimizing capability, and improve the yield and the production efficiency of the production line.

Inventors

DENG KAN
ZHOU RONG
Wu Chuyuan

Assignees

深圳市蔚来电子有限公司

Dates

Publication Date: 20260508
Application Date: 20260127

Claims (10)

1. PCBA production line intelligent monitoring and closed-loop control system based on thing networking perception and data drive, the system includes control terminal, control terminal is configured to carry out following operation: receiving an image comprising a printed circuit board assembly; Determining whether an edge identification mark is included in the image; If the image does not comprise the edge identification mark, commanding the image acquisition device to adjust the position and re-shooting the image comprising the printed circuit board assembly; If it is determined that the edge identification is included in the image, determining whether the image has a correct scaling based on the edge identification; If it is determined that the image has the correct scaling, the image continues to be analyzed.
2. The system of claim 1, wherein continuing to analyze the image comprises: identifying a definition identification mark in the image, wherein the definition identification mark is arranged on the printed circuit board assembly; Determining whether the image has correct sharpness based on the sharpness identification; If it is determined that the image does not have the correct sharpness, commanding the image acquisition device to adjust a focal length and re-capture an image comprising a printed circuit board assembly; If it is determined that the image has the correct sharpness, then the edges of the printed circuit board assembly in the image continue to be identified.
3. The system of claim 2, wherein the control terminal is further configured to: Determining whether the image has the correct orientation based on an edge of the image and an edge of the printed circuit board assembly; If it is determined that the image does not have the correct orientation, adjusting the orientation of the image to the correct orientation and identifying a location identification in the image; if it is determined that the image has the correct orientation, a location identification in the image is identified.
4. A system according to claim 3, wherein the control terminal is further configured to: Determining whether the printed circuit board assembly in the image has a correct position based on the position identification; If it is determined that the printed circuit board assembly in the image does not have the correct position, adjusting the position of the printed circuit board assembly in the image to the correct position; A stencil is superimposed over the printed circuit board assembly in the image with the correct position to divide the printed circuit board assembly in the image into a plurality of zones.
5. The system of claim 4, wherein the plurality of zones comprises a first zone and a second zone, Wherein the control terminal is further configured to: identifying a first defect in the first region; Adjusting a process for machining a printed circuit board assembly in a first way based on the first defect; Identifying a second defect in the second region; a process for machining a printed circuit board assembly is adjusted in a second method based on the second defect, wherein the first method is different from the second method.
6. PCBA production line intelligent monitoring and closed-loop control method based on Internet of things sensing and data driving, wherein the method is executed by a control terminal and comprises the following steps: receiving an image comprising a printed circuit board assembly; Determining whether an edge identification mark is included in the image; If the image does not comprise the edge identification mark, commanding the image acquisition device to adjust the position and re-shooting the image comprising the printed circuit board assembly; If it is determined that the edge identification is included in the image, determining whether the image has a correct scaling based on the edge identification; If it is determined that the image has the correct scaling, the image continues to be analyzed.
7. The method of claim 6, wherein continuing to analyze the image comprises: identifying a definition identification mark in the image, wherein the definition identification mark is arranged on the printed circuit board assembly; Determining whether the image has correct sharpness based on the sharpness identification; If it is determined that the image does not have the correct sharpness, commanding the image acquisition device to adjust a focal length and re-capture an image comprising a printed circuit board assembly; If it is determined that the image has the correct sharpness, then the edges of the printed circuit board assembly in the image continue to be identified.
8. The method of claim 7, wherein the method further comprises: Determining whether the image has the correct orientation based on an edge of the image and an edge of the printed circuit board assembly; If it is determined that the image does not have the correct orientation, adjusting the orientation of the image to the correct orientation and identifying a location identification in the image; if it is determined that the image has the correct orientation, a location identification in the image is identified.
9. The method of claim 8, wherein the method further comprises: Determining whether the printed circuit board assembly in the image has a correct position based on the position identification; If it is determined that the printed circuit board assembly in the image does not have the correct position, adjusting the position of the printed circuit board assembly in the image to the correct position; A stencil is superimposed over the printed circuit board assembly in the image with the correct position to divide the printed circuit board assembly in the image into a plurality of zones.
10. The method of claim 9, wherein the plurality of regions comprises a first region and a second region, Wherein the method further comprises: identifying a first defect in the first region; Adjusting a process for machining a printed circuit board assembly in a first way based on the first defect; Identifying a second defect in the second region; a process for machining a printed circuit board assembly is adjusted in a second method based on the second defect, wherein the first method is different from the second method.

Description

PCBA production line intelligent monitoring and closed-loop control system based on Internet of things sensing and data driving Technical Field The invention relates to the technical field of the Internet of things, in particular to an intelligent PCBA production line monitoring and closed-loop control system based on the Internet of things sensing and data driving. Background Along with the upgrade of electronic manufacturing industry to intelligent manufacturing, the production line of the printed circuit board assembly (Printed Circuit Board Assembly, PCBA) gradually introduces the perception of the Internet of things and the industrial Ethernet and the edge calculation, so as to realize the on-line acquisition and interconnection of equipment state, process parameters, environment and quality data. Based on the continuous perfection of the digital management of the manufacturing execution system (Manufacturing Execution System, MES)/monitoring and data acquisition system (Supervisory Control And Data Acquisition, SCADA) and other systems, the data driving method has increasingly wide application in anomaly detection, process optimization and quality tracing, and can realize finer prediction and scheduling by combining machine learning and digital twin. Meanwhile, the production line control is developed from single-point control to cross-process coordination and closed-loop adjustment, and the improvement of production efficiency, yield and traceability is promoted. Many anomaly detections need to be made based on image data, but the preprocessing techniques of the prior art for image data need to be improved. Disclosure of Invention The invention provides an intelligent monitoring and closed-loop control system of a printed circuit board assembly (Printed Circuit Board Assembly, PCBA) production line based on the perception and data driving of the Internet of things, which comprises a control terminal, wherein the control terminal sequentially performs edge identification detection, scaling verification, definition identification verification and orientation correction by acquiring PCBA images, realizes the self-adaptive adjustment of the position and focal length of an image acquisition device, ensures the consistency of acquired images in proportion, definition and gesture, further completes positioning calibration based on the position identification, and divides a plurality of areas on the PCBA at the correct position by superposing templates, identifies defects of each area and respectively adopts different process adjustment strategies to form closed-loop control. Therefore, the stability and the accuracy of image detection can be improved, the zonal differential parameter adjustment is realized, the defect tracing and process optimizing capability is enhanced, and the yield and the production efficiency of the production line are improved. The invention provides an intelligent PCBA production line monitoring and closed-loop control system based on Internet of things sensing and data driving, which comprises a control terminal, wherein the control terminal is configured to execute the following operations: receiving an image comprising a printed circuit board assembly; determining whether an edge identification mark is included in the image; If the image is determined not to comprise the edge identification mark, the image acquisition device is instructed to adjust the position, and the image comprising the printed circuit board assembly is shot again; If it is determined that the image includes the edge identification, determining whether the image has the correct scaling based on the edge identification; If it is determined that the image has the correct scaling, the image continues to be analyzed. In a preferred embodiment, continuing to analyze the image comprises: Identifying definition identification marks in the image, wherein the definition identification marks are arranged on the printed circuit board assembly; determining whether the image has correct sharpness based on the sharpness identification; if it is determined that the image does not have the correct definition, instructing the image acquisition device to adjust the focal length and re-capture the image including the printed circuit board assembly; If the image is determined to have the correct sharpness, the edges of the printed circuit board assembly in the image continue to be identified. In a preferred embodiment, the control terminal is further configured to: Determining whether the image has the correct orientation based on the edge of the image and the edge of the printed circuit board assembly; If the image is determined to not have the correct orientation, adjusting the orientation of the image to the correct orientation and identifying a position identification in the image; if it is determined that the image has the correct orientation, a location identification in the image is identified. In a preferred embodiment,