Self-adaptive learning method for braking process of heavy trailer

The invention discloses a heavy trailer braking process adaptive learning method, which comprises the following steps of: firstly, establishing a distributed state space model of a heavy trailer by adopting a subspace model identification method, then acquiring a stroke signal and a speed signal by...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: CHEN JIMING, HU JING, PAN YINBIN, ZHANG ZONGYU, LI CHUANWU
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention discloses a heavy trailer braking process adaptive learning method, which comprises the following steps of: firstly, establishing a distributed state space model of a heavy trailer by adopting a subspace model identification method, then acquiring a stroke signal and a speed signal by utilizing a stroke sensor, a speed sensor and the like, and drawing a braking curve; secondly, performing offline BP neural network model training on the acquired or calculated response distance, vehicle speed, braking distance, braking curve variance and average value data and the calculated braking force signal; the trained model is used for predicting the braking distance in the current braking process, and when the braking distance is not within the safety range, prompting and warning are conducted to assist a driver in optimizing the braking behavior. On the basis of the common sensor module of the trailer and in combination with the actual distributed characteristics of the trailer, off-line training and on-l