Sotirios Natsiavas

Drivetrain systems operate under varying operating conditions (OCs), which often obscure early-stage fault signatures and hinder robust condition monitoring (CM). This work introduces an AI digital platform developed during the EEDRIVEN project, featuring a holistic CM framework that integrates statistical time series methods—using Generalized AutoRegressive (GAR) models in a multiple model fault diagnosis scheme—with deep learning approaches, including autoencoders and convolutional neural networks, enhanced through a dedicated decision fusion methodology. The platform addresses all key CM tasks, including fault detection, fault type identification, fault severity characterization, and remaining useful life (RUL) estimation, which is performed using a dynamics-informed health indicator derived from GAR parameters and a simple linear Wiener process model. Training for the platform relies on a limited set of experimental vibration signals from the physical drivetrain, augmented with high-fidelity multibody dynamics simulations and surrogate-model realizations to ensure coverage of the full space of OCs and fault scenarios. Its performance is validated on hundreds of inspection experiments using confusion matrices, ROC curves, and metric-based plots, while the decision fusion scheme significantly strengthens diagnostic reliability across the CM stages. The results demonstrate near-perfect fault detection (99.8%), 97.8% accuracy in fault type identification, and over 96% in severity characterization. Moreover, the method yields reliable early-stage RUL estimates for the outer gear of the drivetrain, with normalized errors < 20% and consistently narrow confidence bounds, which confirms the platform’s robustness and practicality for real-world drivetrain systems monitoring.

In this paper, a new high-performance and memory-efficient contact and road model is developed. Specifically, the road is modeled as a rectangular structured grid of deformable springs in the vertical direction, thus enabling fast execution. The new road model stands out due to its ability to handle large road scenarios by allocating computer memory dynamically for each spring, resulting in efficient memory utilization. Furthermore, each spring represents a small road patch that entails various information, such as the soil elevation, the soil properties, and the soil compaction, allowing for complicated simulations incorporating spatially varying soil properties and phenomena related to the multi-pass effect. In addition, using the new contact model, complex terrain geometries are handled in a computationally efficient way by approximating locally the irregular road profile with a suitable equivalent plane. For this, two different strategies are proposed, namely the radial basis function (RBF) interpolation method and the 3D enveloping contact model. Finally, the proposed techniques are implemented in Altair MotionSolve, a comprehensive multi-body simulation software for complex mechanical systems. In particular, a single-wheel test bed is initially examined followed by a four-wheeled rover model and the next-generation NATO reference mobility model (NG-NRMM). In all cases, the proposed model is validated by using available experimental data. Lastly, a case involving both wheeled and tracked vehicles is also examined by using a shared road model.

In this paper, a new high-performance and memory-efficient contact and road model is developed. Specifically, the road is modeled as a rectangular structured grid of deformable springs in the vertical direction, thus enabling fast execution. The new road model stands out due to its ability to handle large road scenarios by allocating computer memory dynamically for each spring, resulting in efficient memory utilization. Furthermore, each spring represents a small road patch that entails various information, such as the soil elevation, the soil properties, and the soil compaction, allowing for complicated simulations incorporating spatially varying soil properties as well as phenomena related to the multipass effect. In addition, using the new contact model, complex terrain geometries are handled in a computationally efficient way by approximating locally the irregular road profile with a suitable equivalent plane. For this, two different strategies are proposed. Namely, the Radial Basis Function (RBF) interpolation method and the 3D Enveloping contact model. Finally, the proposed techniques are implemented in Altair MotionSolve, a comprehensive multibody simulation software for complex mechanical systems. In particular, a single-wheel test bed is initially examined, followed by a four-wheeled rover model and the Next-Generation NATO reference mobility model (NG-NRMM). In all cases, the proposed model is validated by using available experimental data. Lastly, a case involving both wheeled and tracked vehicles is also examined by using a shared road model.

This study is focused on a critical issue related to the direct and consistent application of Newton’s law of motion to a special but large class of mechanical systems, involving equality motion constraints. For these systems, it is advantageous to employ the general analytical dynamics framework, where their motion is represented by a curve on a non-flat configuration manifold. The geometric properties of this manifold, providing the information needed for setting up the equations of motion of the system examined, are fully determined by two mathematical entities. The first of them is the metric tensor, whose components at each point of the manifold are obtained by considering the kinetic energy of the system. The second geometric entity is known as the connection of the manifold. In dynamics, the components of the connection are established by using the set of the motion constraints imposed on the original system and provide the torsion and curvature properties of the manifold. Despite its critical role in the dynamics of constrained systems, the significance of the connection has not been investigated yet at a sufficient level in the current engineering literature. The main objective of the present work is to first provide a systematic way for selecting this geometric entity and then illustrate its role and importance in describing the dynamics of constrained systems.

Co-simulation techniques are widely used to enable global simulation of a coupled mechanical system via composition of simulators. Within this work, the focus is initially placed on a new scheme for the numerical integration of each subsystem since the corresponding accuracy affects directly the correct solution of a decomposed model. Following that, the new co-simulation methods are introduced. Specifically, a novel coupling strategy for satisfying the coupling conditions in their integral (weak) form, in the time domain, is proposed. This formulation constitutes a general framework for the generation of coupling condition schemes with varying accuracy and stability properties, based on the choice of basis and order of polynomials for the involved quantities, thus creating a whole new perspective on the field of co-simulation. In addition, the point-collocation method, which is mainly employed in the literature, is easily recognized as a degenerate case of this general weak formulation. The essential ideas of the new techniques are initially introduced by utilizing a simple linear model of two masses, constrained with a fixed joint. Subsequently, nonlinear models of a single and a double planar pendulum are investigated for the new numerical integration and co-simulation techniques, respectively. The models examined are relatively simple, but the developed methods have general validity and can be applied for coupling arbitrary multibody or structural solvers.

This study is focused on a critical issue related to the consistent application of Newton’s law of motion to a special but large class of mechanical systems, involving equality motion constraints. For these systems, it is advantageous to employ the general Analytical Dynamics framework, where their motion is represented by a curve on a non-flat configuration manifold. The geometric properties of this manifold, providing the information needed for setting up the equations of motion of the system examined, are fully determined by two mathematical entities. The first of them is the metric tensor, whose components at each point of the manifold are obtained by considering the kinetic energy of the system. The second geometric entity is known as the connection of the manifold. In dynamics, the components of the connection are established by using the set of the motion constraints imposed on the original system and provide the torsion and curvature properties of the manifold. Despite its critical role in the dynamics of constrained systems, the significance of the connection has not been investigated yet at a sufficient level in the current engineering literature. The main objective of the present work is to first provide a systematic way for selecting this geometric entity and then illustrate its role and importance in describing the dynamics of constrained systems.