Speaker
Description
The increasing complexity of industrial systems in the aeronautical sector, together with strict safety, reliability, and energy efficiency requirements, is driving the development of new advanced monitoring and predictive maintenance strategies. In this context, infrared thermography has established itself as a key technology for non-destructive inspection, enabling continuous, real-time, non-contact thermal measurements without interfering with the normal operation of equipment. Its integration with architectures based on the industrial Internet of Things (IoT) and artificial intelligence is of particular interest within the Industry 5.0 paradigm, characterized by the search for more resilient, sustainable, and human-centered industrial systems.
The scope of this study focuses on the development of a predictive monitoring and control system based on distributed industrial IoT devices, infrared sensors, and flow meters, applied to an industrial machine used in material certification processes in the aeronautical sector. The main objective is the early identification of possible wear and deterioration in electrical resistors, as well as the detection of gas fuel leaks in the supply line, through the combined analysis of thermal and energy consumption information.
The proposed solution is based on a network of industrial IoT devices integrated into the plant infrastructure and communicating via standardized industrial protocols. The network nodes incorporate infrared sensors for monitoring the temperature of the resistors, as well as flow meters for quantifying the fuel consumption associated with the thermal process. The system is designed using a hybrid approach, in which data acquisition is performed locally, while intensive processing and advanced analysis are performed in a separate computing center, facilitating scalability, interoperability, and cybersecurity.
Infrared thermography plays a central role in the study as a key sensor for the early detection of anomalies. Deviations in the measured thermal patterns may be associated with aging processes, material degradation, or incipient failures in the resistors. Complementarily, fuel consumption analysis using flow sensors allows deviations from expected behavior to be identified, potentially linked to efficiency losses or leaks in the line. The combination of both sources of information provides a more complete and robust view of the machine's operating status.
Based on the recorded data, a multimodal artificial intelligence model is being developed that can estimate the status of the machine and anticipate abnormal situations. This model learns the correct behavior of the system and exploits the correlations between thermal and consumption variables to improve early detection capabilities compared to approaches based on individual sensors, supporting informed decision-making by operation and maintenance personnel.
This study highlights the potential of infrared thermography integrated with IoT and artificial intelligence to advance toward smarter, more resilient, and sustainable predictive monitoring systems in the aeronautical sector, contributing both to improved operational safety and to the optimization of maintenance costs and energy consumption.
