Remaining useful life (RUL) prediction for FDIA on IoT sensor data using CNN and GRU

Abstract

The industrial Internet of Things (IIoT) is the use of Internet of Things (IoT) technologies in manufacturing which tackles smartly the machine data generated by various sensors and applies various analytics on it to gain useful information. Predictive maintenance (PdM) is a method of preventing asset failure by analyzing production data and identifying patterns to predict issues before they happen. IoT Sensor nodes are also vulnerable to different threats and attacks, which primarily include false data injection attack (FDIA). This paper predicts the accurate remaining useful life (RUL) of IoT device through industrial predictive maintenance (PdM) and exhibits the effect of FDIA on a PdM system through convolutional neural network (CNN) and gated recurrent unit (GRU), for predicting the RUL using the C-MAPSS dataset of a turbo fan engine and gives their comparative result.