Method for producing an electromechanical brake booster, computing unit, electromechanical brake booster
Neural networks and physical models improve the manufacturing efficiency of EBKVs by predicting brake pressure adjustments, reducing cycle time and eliminating manual setup for new variants.
WO2026131053A1PCT designated stage Publication Date: 2026-06-25ROBERT BOSCH GMBH
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- ROBERT BOSCH GMBH
- Filing Date
- 2025-12-01
- Publication Date
- 2026-06-25
Smart Images
Figure EP2025084822_25062026_PF_FP_ABST
Abstract
The invention relates to a method for producing an electromechanical brake booster (EBKV), in which method the electromechanical brake booster is adjusted using a correction parameter (K). According to the invention, a) at least one performance characteristic (F1, F2, F3, F4) is estimated by at least one neural network (N1, N2, N3, N4) on the basis of production data and / or previously determined measured values, and b) the correction parameter (K) is calculated by feeding the at least one performance characteristic (F1, F2, F3, F4) into a physical model (P). The invention also relates to a computing unit and to an electromechanical brake booster.
Need to check novelty before this filing date? Find Prior Art