Airbag controller designed by adaptive-network-based fuzzy inference system (ANFIS)

摘要

An improved algorithm design methodology of vehicle airbag deployment decision is proposed in this paper. Firstly, the vehicle impact severity is analyzed to get four characteristic factors utilized as fuzzy inputs. From these four characteristics factors, the 'two stage fuzzy algorithm' is developed and used as the airbag deployment algorithm for identifying the vehicle impact severity. Finally, the adaptive-network-based fuzzy inference system (ANFIS) is used to train the suitable fuzzy membership functions and fuzzy rules based on crash data for improving the performance of the 'two stage fuzzy algorithm'. Simulation results for different vehicle crash data demonstrate the validity and effectiveness of the proposed design methodology.