Automatic test method and system for detecting mass production PCBA based on thermal infrared imager

Abstract

The invention relates to the technical field of PCBA testing, and provides an automatic testing method and system for detecting mass-produced PCBAs based on a thermal infrared imager, and the method comprises the steps: carrying out the PCBA thermal image video stream collection of a mass-produced PCBA module during the function detection of the mass-produced PCBA module, and forming historical data; training the historical data by using a linear regression machine learning algorithm to form a three-dimensional thermal image standard model database of the PCBA module in combination with a plane dimension and a space dimension in a function test stage and a time dimension; thermal image video stream data of the PCBA module to be tested are collected on line, and the thermal image video stream data are preprocessed; and synchronizing and comparing the preprocessed thermal image video stream data with corresponding three-dimensional thermal image standard model data in a three-dimensional thermal image standard model database, and judging whether the PCBA module to be tested is abnormal or not according to a comparison result. According to the invention, the comprehensiveness and accuracy of testing are improved, and the reliability of mass production of PCBAs is improved.

Claims

1. An automatic testing method for mass-produced PCBA based on infrared thermal imager, characterized in that: include: When the mass-produced PCBA modules are tested for functions, the PCBA thermal image video stream is collected under the functional test state to form historical data; The historical data is trained using a linear regression machine learning algorithm to form a three-dimensional thermal imaging standard model database of the PCBA module in the two dimensions of plane and space combined with the time dimension during the functional testing phase; Collect the thermal video stream data of the PCBA module to be tested online and pre-process the thermal video stream data; The preprocessed thermal imaging video stream data is synchronized and compared with the corresponding stereoscopic thermal imaging standard model data in the stereoscopic thermal imaging standard model database, and it is determined whether the PCBA module to be tested is abnormal based on the comparison result.

2. The automatic testing method for mass-produced PCBA based on infrared thermal imager detection according to claim 1 is characterized in that: When the mass-produced PCBA module is subjected to functional testing, the PCBA thermal image video stream is collected under the functional test state to form historical data, including: While the PCBA function automatic test production line PC performs function testing on the PCBA module, the DO state of the I / O module of the PC is changed in time to trigger the infrared thermal imager to work, and the infrared thermal imager is used to record the infrared thermal image video of the PCBA module in the function test state; According to the PCBA module model and the corresponding function detection program, the delay time is controlled, the DO state of the I / O module of the PC is changed again, and the infrared thermal imager is stopped from recording the infrared thermal image video.

3. The automatic testing method for mass-produced PCBA based on infrared thermal imager detection according to claim 1 is characterized in that: The preprocessing of the thermal image video stream data is as follows: Multi-frame smoothing operation is performed on all pixels in the thermal image video stream data to achieve data denoising.

4. The automatic testing method for mass-produced PCBA based on infrared thermal imager detection according to claim 1 is characterized in that: The pre-processed thermal image video stream data is synchronized and compared with the corresponding stereo thermal image standard model data in the stereo thermal image standard model database, including: Compare the preprocessed thermal image video stream data with the corresponding stereo thermal image standard model data, and synchronize the ambient temperature and timing start time of the two; The thermal image video stream data and the stereo thermal image standard model data are compared and calculated for each frame and each pixel to obtain the comparison result.

5. The automatic testing method for mass-produced PCBA based on infrared thermal imager according to any one of claims 1 to 4, characterized in that: The step of determining whether the PCBA module to be tested is abnormal according to the comparison result includes: Determine whether there is a temperature difference exceeding the limit point according to the comparison result, and execute the next step if there is a temperature difference exceeding the limit point; Determine whether the duration of the temperature difference exceeding limit point and the number of pixels in the area occupied by the temperature difference exceeding limit point exceed the threshold value. If so, it is determined that the PCBA module is abnormal.

6. Automatic test system based on infrared thermal imager to detect mass-produced PCBA, characterized by: include: The historical data acquisition module collects PCBA thermal image video streams in the functional test state to form historical data when the mass-produced PCBA modules are undergoing functional testing; A stereo thermal imaging standard model database forming module uses a linear regression machine learning algorithm to train the historical data to form a stereo thermal imaging standard model database of the PCBA module in the two dimensions of plane and space combined with the time dimension during the functional testing phase; Real-time data acquisition and processing module, which collects the thermal video stream data of the PCBA module to be tested online and pre-processes the thermal video stream data; The data comparison and judgment module synchronizes and compares the preprocessed thermal imaging video stream data with the corresponding stereoscopic thermal imaging standard model data in the stereoscopic thermal imaging standard model database, and determines whether the PCBA module to be tested is abnormal based on the comparison result.

7. An electronic device, characterized in that The invention comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the automatic testing method based on infrared thermal imager detection of mass-produced PCBA as described in any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the automatic testing method based on infrared thermal imager detection of mass-produced PCBA according to any one of claims 1 to 5 is implemented.

Images