Securing reliability and safety is important in several engineering applications (e.g., aerospace, energy, and transportation industries). To do this, we require intelligent monitoring, diagnostic and prognostic methods to characterize anomalies. Moreover, we need to detect faults and predict the remaining useful life (RUL). This is constructed by fusing data preconditioning, signal processing, and analytics of massive machinery data.

Recently, the core technologies in the Fourth Industrial Revolution make the framework prognostics and health management (PHM) more feasible. The reason for this is that data-driven methods significantly enhance their capability to extract highly nonlinear features in measured signals such as vibration, acoustics, emission, pressure, and temperature. This contribution correlates with the development of artificial intelligence (including machine learning and deep learning). Deep neural networks significantly improve the prediction accuracy of PHM technologies for highly complex and nonlinear industrial systems. Therefore, developing effective techniques for addressing deep neural networks in PHM for complex and nonlinear industrial systems is very valuable.

The aim of this Special Issue is to collect original research and review articles highlighting deep neural networks for PHM in complex and nonlinear industrial systems.

Potential topics include but are not limited to the following:

• Sensor and data collection, data quality management, data processing, and data fusion technologies for PHM
• Deep neural networks for structural health monitoring
• Deep neural networks for diagnostics including context definition and awareness, condition monitoring, and anomaly detection
• Deep neural networks for prognostics including severity analysis, prognostics accuracy analysis, and predicting the remaining useful life (RUL)
• Maintenance analytics and maintenance decision optimization
• Deep neural networks including multiscale pyramid, net, transfer learning, and domain adaptation for PHM
• Accelerated life and degradation tests
• Hazard modelling and risk assessment