Fault Diagnosis and Prognostics for Electro-Mechanical Actuators in Aerospace Systems

Electro-mechanical actuators (EMAs) have become integral to modern aerospace platforms, supplanting traditional hydraulic systems in primary and secondary flight controls. Their adoption promises weight savings, reduced environmental impact and simplified installation, but also introduces new reliability challenges. Fault diagnosis seeks to detect and isolate emerging malfunctions—ranging from motor winding shorts and gear train jamming to sensor drift—before catastrophic failure. Prognostics extends this capability by estimating the remaining useful life (RUL) of an actuator, enabling condition-based maintenance and optimised scheduling. Contemporary methods span physics-based models, data-driven algorithms and hybrid approaches that fuse domain knowledge with machine learning. Signal processing techniques extract features from current, voltage, vibration or position data, which feed classification or prediction models. Advances in real-time monitoring, statistical process control and deep learning have elevated diagnostic accuracy under variable operating conditions. The global significance of these developments lies in enhanced flight safety, reduced life-cycle costs and increased availability of More Electric Aircraft and unmanned systems. Practical implementations demonstrate health monitoring on full-scale test rigs, simulation environments and in-service platforms, underscoring the transformative potential of integrated prognostics and health management (PHM) for aerospace EMAs.

Research from Nature Portfolio

No recent Nature Portfolio content available.

Fault Diagnosis and Prognostics for Electro-Mechanical Actuators in Aerospace Systems publication trend

The graph below shows the total number of articles in fault diagnosis and prognostics for electro-mechanical actuators in aerospace systems across all publications each year (not limited to Nature Index journals).

Technical terms

Electro-Mechanical Actuator (EMA): A device that converts electrical energy into mechanical motion for flight control surfaces.

Fault Diagnosis: The process of detecting, isolating and identifying the root cause of system malfunctions.

Prognostics: The estimation of remaining useful life (RUL) based on current and historical system health data.

Remaining Useful Life (RUL): An estimate of the time or usage remaining before a component reaches a defined failure threshold.

Variational Mode Decomposition (VMD): A signal-processing method that decomposes complex data into band-limited intrinsic mode functions.

Multifractal Detrended Fluctuation Analysis (MFDFA): A technique to quantify scaling behaviour and multifractal characteristics in non-stationary signals.

Probabilistic Neural Network (PNN): A feed-forward classification model that estimates class membership probabilities using kernel-based density estimation.

Genetic Algorithm (GA): An optimisation heuristic inspired by natural selection, used to identify model parameters or fault signatures.

Residual Convolutional Neural Network (Rem-CNN): A deep learning architecture incorporating skip connections to extract hierarchical features and mitigate vanishing gradients.

References

1. Fault Diagnosis of Electromechanical Actuator Based on VMD Multifractal Detrended Fluctuation Analysis and PNN. Complexity (2018).
2. Model-Based Fault Detection and Identification for Prognostics of Electromechanical Actuators Using Genetic Algorithms. Aerospace (2019).
3. A Novel 2-D Current Signal-Based Residual Learning With Optimized Softmax to Identify Faults in Ball Screw Actuators. IEEE Access (2020).