Deep Learning for Real-Time Predictive Maintenance and Adaptive Control in Industrial IoT

Abstract

In the context of Industry 4.0 and the Industrial Internet of Things (IIoT),

predictive maintenance has become a major challenge due to the increasing com- plexity of industrial systems and the continuous generation of real-time sensor

data. This thesis presents an intelligent framework that combines Deep Learning and Deep Reinforcement Learning techniques for Remaining Useful Life (RUL) prediction and adaptive maintenance decision-making.The proposed framework consists of two complementary stages. In the first stage, a hybrid CNN-LSTM model is developed to learn degradation features and temporal dependencies from multivariate aircraft engine sensor signals. In the second stage, the predicted

RUL is used by a Soft Actor-Critic (SAC) reinforcement learning agent to sup- port adaptive maintenance optimization and decision-making.The framework is

evaluated using the NASA C-MAPSS datasets under multiple operating condi- tions. Experimental results demonstrate accurate RUL prediction and reliable

maintenance decision-making, leading to a reduction in unexpected failures and

unnecessary maintenance interventions. The obtained results highlight the poten- tial of integrating predictive analytics and adaptive control to support intelligent

maintenance management in Industrial IoT environments.