Anomaly Detection Using Convolutional Neural Network and Generative Adversarial Network

Abstract

<div class="section abstract"><div class="htmlview paragraph">In the automotive embedded system domain, the measurements from vehicle and Hardware-In-Loop are currently evaluated against the testcases, either manually or via automation scripts. These evaluations are localized; they evaluate a limited number of signals for a particular measurement without considering system-level behavior. This results in defect leakage. This study aims to develop a tool that can notify anomalies at the signal level in a new measurement without referring to the testcases, considering a more significant number of system-level signals, thereby significantly reducing the defect leakage. The tool learns important features and patterns of each maneuver from many historical measurements using deep learning techniques. We tried two CNN (convolution neural network) models. The first one is a specially designed CNN that does this maneuver classification and class-specific feature extraction. The second model we tried is the FCN (Fully Convolutional Network) Classification model. CNN-based architecture can be trained faster than the recurrent neural network (RNN) model because it utilizes features extracted from the input data. A Generative Adversarial Network (GAN) model is used in series with the CNN model to clone each of these maneuvers for predicting the anomalies. During the testing phase, the CNN model maps the test measurement to the most similar maneuver from the list of already learned maneuvers, followed by the GAN model outputting the anomalies, if any. To validate the tool, 12 measurements, each of 3 different maneuvers, were selected from an old and matured function in the brake system. The class-specific feature-based classification model resulted in 33% accuracy. However, with the Fully Convolutional Network Classification model, we got 100% accuracy. We injected anomalies in one CSV file for testing purposes. The anomaly detection module predicted all the anomalies correctly. Our future goal is to implement this model at the deployment level.</div></div>