Detect Known Defects, Identify Suspicious Details and Discover Root Causes
The current generation of automated optical/x-ray inspection (AOI/AXI) solutions can recognize and remove parts with expected defects. But what about the defects that we don’t know about? How about slow deterioration due to equipment aging or changes in the quality of raw materials? Those may cause your next recall. That’s where numericcal’s POINTER system comes in. POINTER looks for known defects as well as suspicious details on every unit going through your production line. It labels and prioritizes suspicious areas for QA/QC review. This human input allows POINTER to further learn thus generating a positive feedback loop to increase accuracy. POINTER is the fastest way to error-proof a production line and maximize its yield.
With POINTER, the Possibilities Are Endless
Whether you are looking to improve yield with fine-grained AOI/AXI or to reduce the labor-intensive sampling and inspection, numericcal’s POINTER system can help. In the examples below, POINTER identifies faulty printed circuit boards (PCBs) and fabrics after being trained only on what the proper examples should look like.
POINTER enhances your QA/QC team, and saves them time by having them only inspect suspicious items.
POINTER prevents potentially large product losses common with batch type QA/QC sampling.
POINTER provides comprehensive view of potential issues to enable root cause analysis and identify latent defects.
POINTER increases yield since your process line is operating with higher reliability with less QA/QC-caused stoppage.
Optimize Yield and Keep an Eye on High-Priority Issues
POINTER actively learns from your QA/QC team’s feedback to adjust to your process and production line. This inherently dynamic nature of the POINTER system results in a major reduction in faulty items passing undetected through the QA/QC process, thus eliminating production losses and recalls. Application of POINTER’s root cause analysis functionality allows for the detection of latent defects at early stages in your processes thus providing insights on how to improve long term yields.
Applicable in
