CN-122008188-A - System and method for processing board passing of circuit board assembly

Abstract

The invention relates to the technical field of PCBs and discloses a board passing processing system and method of a circuit board assembly. The system comprises a multipath area array camera, an AI reasoning server, a communication module, a conveyor belt control end and a mobile mechanical arm control end, wherein the multipath area array camera is used for collecting real-time images of circuit board components on a conveyor belt of a production line, the AI reasoning server is used for analyzing images collected by the multipath area array camera to identify whether any abnormal condition of component distance, component overlapping, component folding or component deflection exists in the circuit board components, the communication module is used for sending an abnormal processing instruction generated when the AI reasoning detects that an abnormal state exists to the conveyor belt control end and the mobile mechanical arm control end, the conveyor belt control end is used for controlling the conveyor belt to stop running when the abnormal processing instruction sent by the communication module is received, the mobile mechanical arm is used for recovering the conveyor belt to run when the conveyor belt is received, and the mobile mechanical arm is used for identifying, positioning, grabbing and returning the abnormal circuit board components according to a coordinate range given by the AI reasoning during the stop running of the conveyor belt and outputting a completion instruction after the processing is completed.

Inventors

• WANG FUJIANG
• FAN YAQIN

Assignees

• 深南电路股份有限公司

Dates

Publication Date

20260512

Application Date

20260106

Claims (10)

1. 1. A board passing processing system for a circuit board assembly, comprising: The multi-road-surface array camera is used for collecting real-time images of the circuit board assemblies on the production line conveyor belt; the AI reasoning server is used for analyzing the images acquired by the multipath area array cameras to identify whether any abnormal condition of component distance, component overlapping, component folding or component deflection exists in the circuit board component; the communication module is used for sending an abnormal processing instruction generated by the AI reasoning server when the AI reasoning server detects that an abnormal state exists to the conveyor belt control end and the mobile mechanical arm control end; The conveyor belt control end is used for controlling the conveyor belt to stop running when an exception handling instruction sent by the communication module is received, and recovering the conveyor belt to run when a completion instruction is received; and the mobile mechanical arm is used for identifying, positioning, grabbing and homing the abnormal circuit board assembly according to the coordinate range given by the AI reasoning server during the stop operation of the conveyor belt, and outputting a completion instruction after the processing is completed.
2. 2. The system of claim 1, wherein the AI inference server is configured to identify at least one of the following abnormal conditions: The distance between adjacent circuit board assemblies is smaller than the distance of a preset threshold value; overlapping the edge areas of the circuit board assembly in a mutually covering manner; The circuit board assembly has a bent or deformed fold; The placement angle of the circuit board assembly on the conveyor belt deviates from a deflection of a preset reference angle range.
3. 3. The system of claim 1, wherein the mobile robotic arm comprises: The control host is used for receiving an exception handling instruction issued by the AI reasoning server; The motion executing mechanism is provided with a plurality of joint degrees of freedom and is used for completing movement, rotation and grabbing actions; the tail end clamp is used for clamping and placing the abnormal circuit board assembly; And the binocular vision positioning module is used for acquiring the spatial position information of the circuit board assembly and transmitting the spatial position information to the control host so as to realize the positioning operation of the circuit board assembly.
4. 4. The system of claim 3, wherein the mobile robotic arm further comprises: The moment sensor is used for detecting the stress condition of the tail end clamp in the grabbing or carrying process; the anti-collision mechanism is used for sensing contact with external obstacles and limiting the action of the mechanical arm in the movement process; and the control feedback unit is used for transmitting the data acquired by the moment sensor and the anti-collision mechanism to the control host.
5. 5. The system of claim 1, wherein the AI reasoning server further comprises: a model management unit for storing a plurality of AI visual recognition models based on deep learning; The updating unit is used for receiving externally input model updating data and replacing, expanding or version upgrading the AI visual identification model; the feature extraction unit is used for preprocessing the image data from each production line to generate corresponding image feature vectors; The model calling scheduling unit is used for matching the image feature vector generated by the feature extraction unit with a preset line model index table, determining an AI visual recognition model corresponding to the current line, and calling the model to execute the image recognition task of the circuit board assembly of the corresponding line; And the model switching unit is used for switching the identification model adopted by the AI reasoning server into a corresponding target model when the image data input of different production lines is detected.
6. 6. The system of claim 1, wherein the communication module is a WiFi6-NCP low power communication module, comprising: the wireless data access unit is used for receiving an exception handling instruction output by the AI reasoning server; and the wireless data sending unit is used for sending the abnormality processing instruction to the conveyor belt control module and the mobile mechanical arm.
7. 7. The system of claim 1, wherein the conveyor belt control end comprises: the stop instruction receiving unit is used for stopping the operation of the conveyor belt when receiving the stop instruction sent by the communication module; the recovery instruction receiving unit is used for restarting the conveyor belt when receiving the recovery instruction sent by the communication module; and the control interface unit is used for carrying out electric signal connection with the conveyor belt driver to realize the switching of the running state of the conveyor belt.
8. 8. The system of claim 1, further comprising a background log management module, the background log management module comprising: A data receiving unit for receiving the abnormality determination result of the AI reasoning server; A data storage unit configured to store the abnormality determination result; and the report generation unit is used for generating an abnormal event report related to the production line according to the stored abnormal judgment result.
9. 9. The system of claim 1, wherein the multi-way area array camera is an industrial camera and comprises: The imaging sensor is used for acquiring images of the surface of the circuit board assembly; the data interface module is used for transmitting the image data acquired by the imaging sensor to the AI reasoning server through a network interface; And the mounting bracket is used for fixedly arranging the area array camera at different positions of the production line.
10. 10. A board passing processing method of a circuit board assembly is characterized by comprising the steps of carrying out real-time image acquisition on the circuit board assembly on a production line conveyor belt by a multi-road-surface-array camera, transmitting acquired image data to an AI reasoning server, analyzing the image data in the AI reasoning server to judge whether the circuit board assembly has any abnormal condition of over-close assembly distance, assembly overlapping, assembly folding or assembly deflection, generating an abnormal processing instruction by the AI reasoning server and sending the abnormal processing instruction to a conveyor belt control end and a mobile mechanical arm through a communication module when the abnormal condition is detected, enabling the conveyor belt to stop running by the conveyor belt control end after receiving the abnormal processing instruction, carrying out identification, positioning, grabbing and homing operation on the abnormal circuit board assembly by the mobile mechanical arm according to the abnormal processing instruction and a given coordinate range, and sending a completion instruction to the conveyor belt control end after the abnormal circuit board assembly is processed by the mobile mechanical arm, and recovering running of the conveyor belt after receiving the completion instruction by the conveyor belt control module.

Description

System and method for processing board passing of circuit board assembly Technical Field The invention relates to the technical field of PCB processing, in particular to a board passing processing system and method of a circuit board assembly. Background The circuit board assembly in the electronic assembly industry needs to be subjected to a plurality of technological treatments such as solder paste, visual inspection, finished product inspection and the like, wherein the technological treatments need to be subjected to board action flow. In the process of finished inspection or internal inspection in the printed electronic circuit industry, surface quality detection needs to be performed on TOP surfaces and BOTTOM surfaces of circuit board surfaces, and the circuit board components are usually transported through guide rails. In actual production, the problems of abrasion of a sliding rail element, insufficient maintenance of sliding rail engine oil and the like often cause collision or overlapping of the circuit board assemblies in the front and back close to each other, so that the clamping plate cannot enter the next working procedure. In the past time, the intelligent level of the PCB industry is greatly improved, but in the nonstandard automatic cardboard intervention flow, manual intervention operation is still needed, and the responsibility people of a production line group, engineers and upstream and downstream procedures are coordinated, so that the manual intervention has great variability and instability. Therefore, under the background of advocating intelligent manufacturing, full-automatic flow, night factories and the like, a set of full-automatic board-passing solution without interference is urgently designed, so that the problem that the existing PCB board-passing process has a complicated flow requiring manual participation is solved. Disclosure of Invention Based on the above, it is necessary to provide a system and a method for processing a board assembly by using a set of full-automatic board-passing solution without interference to solve the problem caused by manual participation in board-passing processing. A board passing processing system of a circuit board assembly, comprising: The multi-road-surface array camera is used for collecting real-time images of the circuit board assemblies on the production line conveyor belt; the AI reasoning server is used for analyzing the images acquired by the multipath area array cameras to identify whether any abnormal condition of component distance, component overlapping, component folding or component deflection exists in the circuit board component; the communication module is used for sending an abnormal processing instruction generated by the AI reasoning server when the AI reasoning server detects that an abnormal state exists to the conveyor belt control end and the mobile mechanical arm control end; The conveyor belt control end is used for controlling the conveyor belt to stop running when an exception handling instruction sent by the communication module is received, and recovering the conveyor belt to run when a completion instruction is received; and the mobile mechanical arm is used for identifying, positioning, grabbing and homing the abnormal circuit board assembly according to the coordinate range given by the AI reasoning server during the stop operation of the conveyor belt, and outputting a completion instruction after the processing is completed. Further, the AI reasoning server is configured to identify at least one of the following abnormal situations: The distance between adjacent circuit board assemblies is smaller than the distance of a preset threshold value; overlapping the edge areas of the circuit board assembly in a mutually covering manner; The circuit board assembly has a bent or deformed fold; The placement angle of the circuit board assembly on the conveyor belt deviates from a deflection of a preset reference angle range. Further, the mobile robot arm includes: The control host is used for receiving an exception handling instruction issued by the AI reasoning server; The motion executing mechanism is provided with a plurality of joint degrees of freedom and is used for completing movement, rotation and grabbing actions; the tail end clamp is used for clamping and placing the abnormal circuit board assembly; And the binocular vision positioning module is used for acquiring the spatial position information of the circuit board assembly and transmitting the spatial position information to the control host so as to realize the positioning operation of the circuit board assembly. Further, the mobile robot arm further includes: The moment sensor is used for detecting the stress condition of the tail end clamp in the grabbing or carrying process; the anti-collision mechanism is used for sensing contact with external obstacles and limiting the action of the mechanical arm in the movement process; and the control feedb