· Detection object: proton membrane surface coating products
Using a large line-scanning camera and a high-brightness light source, after the coating is dried and before entering the compound process, the encoder is used to trigger the camera to take pictures, and the acquisition card is used to obtain and link the pole piece images, and the surface of the coated surface is detected by software algorithms Quality, automatically identify defects and determine whether it is NG or not, label and mark NG incoming materials by itself, and self-check whether the label is affixed. At the same time, it has the function of statistics and storage of bad data.
· Detection accuracy: defect size>0.3mm×0.3mm.
· Applicable products: Detection of the proton membrane after coating and drying.
· Detection accuracy rate: missed judgment rate ≤ 1%, false positive rate ≤ 1%.
· Model switching: the entered model switching ≤15min.
Defect category | Defect characteristics | Definition | Specification |
leaky substrate | leaky substrate | Surface coating peeled off or uncoated and leaks out of substrate subfilm | 0.3mm×0.3mm |
Streak | Crease/wrinkle | Fold marks where the substrate was bent, but did not leak the substrate | Width≥0.5mm Length≥2mm Width and length at the same time meet the condition of gray value difference > 30 |
Incomplete/broken | Substrate is incomplete or cracked or damaged |
Crack / crack | Substrate material membrane diaphragm cracked and striped |
Scratches/Scratches/Scratches/Indentations | Minor scratches/scratches/gouges/bruises on the surface of the coated area, but no leakage of metal |
Spot | Dark spot/white spot | Black/white speckle characteristic in the coating | Diameter≥0.5mm Gray value difference > 30 |
Particles | Particles/foreign matter | Foreign matter or particles mixed in the coating material | Diameter≥0.5mm Gray value difference > 30 |
