AI tool from Viprotron revolutionizes glass quality control: efficiency increase, better delivery quality and cost savings
Better classification algorithms lead to faster reliable results
The use of three different inspection channels in Quality Scanner 3D already provides highly reliable classification results. Viprotron has many years of experience and proven algorithms for correct defect classification. For example, a glass scratch can be distinguished from a coating scratch or even more similar optical defects, such as a bubble from a water drop, with a high probability.
Nevertheless, there is always potential for improvement, especially in the case of similar defects. The use of AI tools is therefore the next step. But what process steps are required and what requirements must be taken into account?
Our new Viprotron application software Rel. 9.x also allows customers to report unclear classifications directly by sending us the error image and the correct classification result. We qualify this data and feed it into the AI tool to develop an even more sophisticated training and evaluation model.
First, the data requirements are determined. Thanks to our 20 years of experience in image processing, we have high-quality and reliable data sets. In addition, we continuously generate new data to close the gap of the last, incorrectly classified defects with compliant data. In doing so, we use a reliable filter to aggregate comparable data.
The AI tool uses all existing data, algorithms, new information and the results of the learning process to increase the reliability of the classifications. This avoids inaccurate or unclear defect classifications. This enables improved root cause analysis and an increase in productivity because no line has to be stopped due to incorrect classification (e.g. water drop instead of bubble).
In addition to higher productivity, this leads to better delivery quality and more reliable statistics. The more staff can rely on the scanner's classification, the shorter the inspection time per glass. Low-quality glass is reliably detected and removed from the process, resulting in better delivery quality.
Better classification also enables more meaningful statistical reports for the quality manager for root cause analysis. Overall, these improvements help our customers simplify processes, save costs, and strengthen their image through fewer complaints.
Would you also like to take advantage of this improved defect detection?