Name
Abstract | ||
|---|---|---|
Optical systems are a popular choice for quality inspection because they are not only contactless and precise but also comparably fast. Measurement speed is an important issue, especially for safety-relevant products where 100% quality inspection is required. This is particularly true for micro products, which have higher variances due to so called size effects. These size effects make inspection more difficult because much more relevant influence factors exist at the micro than at the macro level. However, the issue is not solved by finding the right metrology. With production rates of micro cold forming processes with multiple parts per second, manual inspection is not feasible anymore. Automatic systems are required in order to inspect more than one million parts per lot. Thereby, besides fast metrology and handling systems, efficient algorithms are needed. Particularly in the face of high variances the foundation for such algorithms needs to be the detection of anomalies/areas of interest, as unknown defects may occur. Detected anomalies can subsequently be subjected to further processing, such as classification or the application of tolerances. Here we propose a fast method for the automatic detection of anomalies along the outer walls of circular objects. First tests of our method in the context of wrinkle detection in cold formed metal micro cups show promising results. We also show that due to low computational cost the method is applicable for mobile solutions, e.g. to aid human inspection. |
Year | Venue | Field |
|---|---|---|
2016 | SummerSim | Anomaly detection,Forming processes,Simulation,Computer science,Metrology,Real-time computing,Macro |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
3 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Benjamin Staar | 1 | 0 | 0.34 |
| Michael Lütjen | 2 | 2 | 2.16 |
| michael freitag | 3 | 11 | 8.33 |