Remedy: Automated Design and Deployment of Hybrid Deep Learning-based Error Detectors

Modern Cyber-Physical Systems are characterized by dynamic and complex structure. They are facing factors such as erroneous software update, Artificial Intelligence components, reconfigurable structure, etc. Because of that, they are prone to latent or dormant faults. With the growth of data that needs to be processed, traditional error-handling mechanisms are failing to be efficient enough. For this reason, Deep Learning methods come into play. Application of such methods for detection and handling of error is nowadays a vastly used approach. However, the development of Deep Learning-based error detectors is time-consuming because there is no general approach to automatically exploit the specifics of the given system. In order to effectively address this issue, we propose a new hybrid deep learning-based methodology called Remedy. It comprises three steps: (1) identification of critical fault parameters, (2) automatic search for efficient access points for training data generation, and (3) deployment of deep learning-based error detector. To illustrate the effectiveness of this methodology, we present an implementation example on a classical Simulink model. Comparing the results with the corresponding baseline, the authors discuss the advantages and disadvantages of the proposed method.