NVH METHOD AND APPARATUS FOR PREDICTING THE PERFORMANCE OF A VEHICLE NVH SYSTEM BASED ON DEEP LEARNING

A method for predicting a performance of a vehicle NVH system based on deep learning according to one embodiment of the present invention may comprise: a step of performing pre-processing for the learning data collected for each channel related to noise and vibration while driving; a step of perform...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: SONG DAE HUN, LEE MOON SEOK, HAN EUN JUN, PARK SANG BEOM, AHN YOUNG KWAN
Format: Patent
Sprache:eng ; kor
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A method for predicting a performance of a vehicle NVH system based on deep learning according to one embodiment of the present invention may comprise: a step of performing pre-processing for the learning data collected for each channel related to noise and vibration while driving; a step of performing model learning to construct a correlation function between multiple inputs and multiple outputs corresponding to the pre-processed learning data using an artificial neural network; and a step of predicting a performance using a vehicle NVH system model constructed through the model learning. 본 발명의 일 실시 예에 따른 딥러닝 기반 차량 NVH 시스템의 성능 예측 방법은 주행 중 소음 및 진동 관련 채널 별 수집된 학습 데이터에 대한 전처리를 수행하는 단계와 인공신경망을 이용하여 상기 전처리된 학습 데이터에 상응하는 다중 입력과 다중 출력 사이의 상관 관계 함수를 구성하는 모델 학습을 수행하는 단계와 상기 모델 학습을 통해 구성된 차량 NVH 시스템 모델을 이용하여 성능을 예측하는 단계를 포함할 수 있다.