Vehicle actuator fault detection apparatus and detection method

Abstract

The present disclosure relates to a vehicle actuator failure detection apparatus and detection method, the vehicle actuator failure detection apparatus comprising: a training device that trains a model using training data including behavior data of a vehicle and a steering compensation angle; and a controller detecting a failure of an actuator in the vehicle based on the model.

Description

[0001] Cross References to Related Applications [0002] This application claims priority from Korean Patent Application No. 10-2020-0108517 filed with the Korean Intellectual Property Office on Aug. 27, 2020, the entire contents of which are incorporated herein by reference. technical field [0003] The present disclosure relates to a vehicle actuator fault detection technology based on deep learning. Background technique [0004] In general, deep learning (or deep neural networks) is a type of machine learning that has multiple layers of artificial neural networks (ANNs) between inputs and outputs. According to the structure, the problem to be solved, the purpose, etc., the artificial neural network may include a convolutional neural network (CNN), a recurrent neural network (RNN), and the like. [0005] The data input to the convolutional neural network is divided into training set and test set. The convolutional neural network learns the weight of the neural network th...

AI Technical Summary

Problems solved by technology

Therefore, the problem with the prior art is that it is impossible to accurately detect whether the actuator in the vehicle is malfunctioning due to the complexity of controlling the vehicle

Images