Method and device for determining the similarity of parallel manufacturing machines
The method uses histograms and vector angles to assess the similarity of parallel manufacturing machines, addressing the unreliability of existing methods and enabling efficient troubleshooting of yield issues in manufacturing processes.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- ROBERT BOSCH GMBH
- Filing Date
- 2026-01-14
- Publication Date
- 2026-07-23
AI Technical Summary
Existing methods for determining the similarity of parallel manufacturing machines are unreliable and computationally intensive, failing to provide practical insights into the actual similarity of process results, and cannot effectively diagnose yield problems in manufacturing processes.
A method using histograms to compare the distribution of measured values from parallel manufacturing machines, calculating the angle between vectors derived from these histograms to determine similarity, and identifying the production machine with the most probable process deviation by tracing batches with low yield.
Provides a reliable and automatable diagnosis of yield problems by accurately assessing the similarity of manufacturing processes, enabling rapid identification of deviations and optimizing production settings.
Smart Images

Figure EP2026050726_23072026_PF_FP_ABST