•  
  •  
 

Keywords

Aircraft SHM, Smart sensors, Damage detection, Machine learning, Hybrid SHM models, Data-driven monitoring

Document Type

Article

Abstract

Structural Health Monitoring (SHM) systems are essential technologies that contribute to enhancing the safety, reliability, and efficiency of aircraft structures throughout their operational lifespan. With the increasing use of lightweight materials and complex structural designs, coupled with longer maintenance intervals, traditional scheduled inspection methods have become insufficient, leading to a shift towards continuous, sensor-based monitoring systems. This research aims to provide a systematic and comprehensive review of the latest developments in aircraft structural health monitoring, focusing on sensing technologies, data collection methods, and intelligent processing techniques based on artificial intelligence. This study is based on a systematic analysis of the scientific literature published between 2016 and 2025, using established scientific databases. The study addresses various types of sensors, including piezoelectric, fiber optic, stress, and vibration sensors, as well as signal processing techniques and machine learning algorithms capable of handling complex, high-dimensional data. The performance of these technologies is also evaluated under realistic operating conditions, highlighting the challenges related to uncertainty, scalability, and immediate deployment. The results of this review demonstrate a growing trend toward intelligent, data-driven systems, highlighting the need to develop realistic databases, improve model interpretability, and adopt hybrid models that combine physical methods with artificial intelligence. This study provides important scientific insights that contribute to the development of more efficient and reliable SHM systems, supporting improved aerospace safety and reduced maintenance costs.

DOI

10.30684/2412-0758.1569

First Page

111

Last Page

135

Download

Share

COinS