Air tightness detection water body updating method and system based on artificial intelligence

Abstract

The invention provides an air tightness detection water updating method and system based on artificial intelligence, and relates to the field of artificial intelligence. The method comprises the following steps: irradiating a water tank with a laser, collecting a sample image, preprocessing the image, and segmenting the image into an imaging point detection image and a bubble detection image; performing threshold segmentation on the imaging point detection image according to the updated initial threshold to obtain an imaging point area, and taking a difference between the imaging point areas of the current frame of imaging point detection image and the first frame of imaging point detection image as water turbidity; carrying out superposition operation on the bubble detection image, then carrying out semantic segmentation, obtaining an ROI region image of the bubble, and calculating the ROI region image by using an SMD2 function to obtain definition; if the ROI is not detected, judging that water needs to be changed when the turbidity is greater than the turbidity threshold value; and if the ROI is detected, judging that water needs to be changed when the turbidity is greater than a turbidity threshold and the definition is smaller than a fuzzy threshold. According to the method, the change of turbidity can be sensitively reflected, the robustness is good, and the air tightness evaluation of the precision workpiece is more accurate.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to an artificial intelligence-based airtightness detection water update method and system. Background technique [0002] At present, there are many air tightness detection technologies for workpieces, such as: differential pressure method, direct pressure method, flow quantitative method, bubble detection method, etc. The traditional bubble detection method is more commonly used and has a lower cost. The bubble detection method is easily affected by the turbidity of the water body when detecting bubbles. When the turbidity of the water body increases, it will increase the difficulty of detecting the bubbles. At this time, some image processing methods can be used to increase the clarity of the bubble area; At this time, the characteristics of the bubbles are not obvious, or even disappear. In order to ensure the accuracy of the test results, the water body must be replaced. ...

AI Technical Summary

Problems solved by technology

[0002] At present, there are many air tightness detection technologies for workpieces, such as: differential pressure method, direct pressure method, flow quantitative method, bubble detection method, etc. The traditional bubble detection method is more commonly used and has a lower cost. The bubble detection method is easily affected by the turbidity of the water body when detecting bubbles. When the turbidity of the water body increases, it will increase the difficulty of detecting the bubbles. At this time, some image processing methods can be used to increase the clarity of the bubble area; When the air bubbles are not obvious, or even disappear, in order to ensure the accuracy of the test results, the water body must be replaced

[0003] Commonly used water turbidity detection methods include spectrophotometry, visual turbidity, etc. However, in the application scene of air tightness detection, the accuracy of spectrophotometry is not high, and visual turbidity is difficult to unify the standard, and Too much human resources

Images