Domenico Fabio Migliore
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Domenico Fabio Migliore has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
Enrico Fraccaroli
University of Verona,Department of Engineering for Innovation Medicine,Italy
2 shared publicationsFrancesco Acerra
Leonardo S.p.A.,Turin,Italy
2 shared publications- Francesco Biondani
Department of Engineering for Innovation Medicine, University of Verona, 37134 Verona, Italy
2 shared publications Franco Fummi
University of Verona,Department of Engineering for Innovation Medicine,Italy
2 shared publications- Massimo Sorli
Department of Mechanical and Aerospace Engineering, Politecnico di Torino, 10129 Torino, Italy
2 shared publications Nicola Dall'ORa
University of Verona,Department of Engineering for Innovation Medicine,Italy
2 shared publications
Latest Publications
- Open Access
A Custom Genetic Algorithm Framework for Early-Stage Optimization of Electromechanical Actuators
This work presents a systematic methodology for the preliminary design and optimization of electromechanical actuators, aimed at minimizing overall mass and rotational inertia while satisfying torque and speed requirements. The proposed approach integrates dimensionless scaling relationships, derived and corrected from catalog data, with a genetic algorithm that performs multi-parameter optimization across different actuator architectures. The algorithm enables the exploration of non-linear and multi-modal design spaces, allowing the identification of balanced solutions between mechanical efficiency and dynamic performance, employing custom functions for individual generation, constraint handling, and compatibility verification to ensure feasible and consistent architecture designs throughout the optimization process. A case study on the steering system of an aircraft nose landing gear illustrates the method’s ability to define optimal design parameters in real mechanical systems. Linear and non-linear dynamic analyses confirmed the compliance of the optimized design with control and stability requirements. The study demonstrates how the developed custom constrained genetic optimization approach can effectively support the early design phase, reducing the computational effort required in further stages and improving the overall consistency of electromechanical actuator development.
Open AccessA Custom Genetic Algorithm Framework for Early-Stage Optimization of Electromechanical Actuators
This work presents a systematic methodology for the preliminary design and optimization of electromechanical actuators, aimed at minimizing overall mass and rotational inertia while satisfying torque and speed requirements. The proposed approach integrates dimensionless scaling relationships, derived and corrected from catalog data, with a genetic algorithm that performs multi-parameter optimization across different actuator architectures. The algorithm enables the exploration of non-linear and multi-modal design spaces, allowing the identification of balanced solutions between mechanical efficiency and dynamic performance, employing custom functions for individual generation, constraint handling, and compatibility verification to ensure feasible and consistent architecture designs throughout the optimization process. A case study on the steering system of an aircraft nose landing gear illustrates the method’s ability to define optimal design parameters in real mechanical systems. Linear and non-linear dynamic analyses confirmed the compliance of the optimized design with control and stability requirements. The study demonstrates how the developed custom constrained genetic optimization approach can effectively support the early design phase, reducing the computational effort required in further stages and improving the overall consistency of electromechanical actuator development.
- 20 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
GAIA: A Comprehensive Pipeline for Enabling Aircraft Digital Twin Creation
The integrity and reliability of Landing Gear Systems (LGSs) are crucial for aircraft safety. However, the scarcity of real-world fault data hinders the creation of effective Predictive Maintenance (PdM) strategies, especially those that rely on modern Machine Learning (ML) techniques. As a result, this article presents GAIA: the first comprehensive pipeline that enables the creation of digital twins to support PdM in the aviation domain. Specifically, combining multi-physics modeling and data-driven techniques, GAIA allows learning models to achieve superior performance in fault detection and diagnosis tasks. As a use case, we consider a LGS system, and introduce DSLG D/R, a novel dataset specifically designed for LGS fault classification, created in collaboration with Leonardo S.p.A. Our results demonstrate a significant 10.56% improvement in fault classification accuracy compared to other data augmentation methods. To further demonstrate the applicability of our method, we also evaluated it on the Electrical Fault dataset, a well-established benchmark for the diagnosis of power system faults, highlighting the GAIA versatility across different critical safety domains. The code and dataset are available at https://github.com/esd-univr/GAIA.
- 20 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
GAIA: A Comprehensive Pipeline for Enabling Aircraft Digital Twin Creation
The integrity and reliability of Landing Gear Systems (LGSs) are crucial for aircraft safety. However, the scarcity of real-world fault data hinders the creation of effective Predictive Maintenance (PdM) strategies, especially those that rely on modern Machine Learning (ML) techniques. As a result, this article presents GAIA: the first comprehensive pipeline that enables the creation of digital twins to support PdM in the aviation domain. Specifically, combining multi-physics modeling and data-driven techniques, GAIA allows learning models to achieve superior performance in fault detection and diagnosis tasks. As a use case, we consider a LGS system, and introduce DSLG D/R, a novel dataset specifically designed for LGS fault classification, created in collaboration with Leonardo S.p.A. Our results demonstrate a significant 10.56% improvement in fault classification accuracy compared to other data augmentation methods. To further demonstrate the applicability of our method, we also evaluated it on the Electrical Fault dataset, a well-established benchmark for the diagnosis of power system faults, highlighting the GAIA versatility across different critical safety domains. The code and dataset are available at https://github.com/esd-univr/GAIA.
- 18 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Fault Injection for Synthetic Data Generation in Aircraft: A Simulation-Based Approach
The safety of aircraft heavily depends on the integrity of the Landing Gear System (LGS). However, gathering real-world fault data to support effective Prognostic and Health Management (PHM) practices presents significant challenges. This work proposes a novel methodology for generating synthetic fault data using a multi-physics Simscape model of a landing gear deployment/retraction mechanism. The model incorporates specialized fault blocks designed to replicate various hydraulic failure modes, aiming to broaden the pool of fault data covering the most common failures. This approach promises to enhance maintenance strategies and facilitate the development of hybrid Model-Based and Data-Driven solutions. Ultimately, the results of this study will be used to understand the physics within the landing gear better and gather the necessary data to create an effective Digital Twin for predictive maintenance.
- 18 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Fault Injection for Synthetic Data Generation in Aircraft: A Simulation-Based Approach
The safety of aircraft heavily depends on the integrity of the Landing Gear System (LGS). However, gathering real-world fault data to support effective Prognostic and Health Management (PHM) practices presents significant challenges. This work proposes a novel methodology for generating synthetic fault data using a multi-physics Simscape model of a landing gear deployment/retraction mechanism. The model incorporates specialized fault blocks designed to replicate various hydraulic failure modes, aiming to broaden the pool of fault data covering the most common failures. This approach promises to enhance maintenance strategies and facilitate the development of hybrid Model-Based and Data-Driven solutions. Ultimately, the results of this study will be used to understand the physics within the landing gear better and gather the necessary data to create an effective Digital Twin for predictive maintenance.
- 23 April 2022
- Published by Springer Nature
- p. 28-35
Simulation of the Effects of Backlash on the Performance of a Collaborative Robot: A Preliminary Case Study
- 23 April 2022
- Published by Springer Nature
- p. 28-35
Simulation of the Effects of Backlash on the Performance of a Collaborative Robot: A Preliminary Case Study