Fabricio Machado
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fabricio Machado has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Ali Emadi
Department of Electrical and Computer Engineering and McMaster Automotive Resource Centre (MARC), McMaster University, Hamilton, ON L8S 4L8, Canada
4 shared publications - Atriya Biswas
Department of Engineering Design, IIT MADRAS, Chennai, India
2 shared publications - Daniel Goretti Barroso
McMaster Automotive Resource Centre, McMaster University, Hamilton, ON, Canada
2 shared publications - Eduardo Louback
McMaster Automotive Resource Centre, McMaster University, Hamilton, ON L8P 0A6, Canada
1 shared publication - Fengjun Yan
McMaster Automotive Resource Center, McMaster University, Hamilton, ON, Canada
1 shared publication - Hao Wang
Monash University
1 shared publication
Latest Publications
- 29 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 12 (1) , 392-404
Safe Deep Reinforcement Learning for Energy Management of Electrified Vehicles: Optimal Action Filtering and Battery-in-the-Loop Validation
Despite the promising performance of deep reinforcement learning (DRL)-based energy management systems (EMSs) for electrified vehicles, persistent safety concerns regarding control actions hinder their real-world deployment. This article proposes a safe DRL-based EMS for hybrid electric vehicles (HEVs) that guarantee zero safety violations during both training and deployment. A model-based safety layer is developed with prior knowledge to filter unsafe actions with minimal disruption to agent exploration. This safety metric evaluation is embedded into the reward function via a Lagrangian relaxation (LR) method, enabling adaptive penalization of constraint violations and prompting efficient policy learning. A safe soft actor–critic (SSAC) EMS is then trained under stochastic conditions, including random initial battery state-of-charge (SOC) and multimodal driving cycles. The approach is validated through simulation and battery-in-the-loop (BIL) experiments. The proposed reward formulation accelerates safety-aware policy learning by 38.5% compared to conventional methods. In BIL tests, SSAC-EMS achieves over 95% fuel efficiency relative to the offline dynamic programming (DP) benchmark under unseen driving cycles and initial SOCs, with actions consistently respecting safety constraints. Compared to the adaptive equivalent consumption minimization strategy (AECMS), SSAC-EMS improves fuel economy by 6%–10% while delivering more stable SOC regulation and smoother engine operation.
- 29 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 12 (1) , 392-404
Safe Deep Reinforcement Learning for Energy Management of Electrified Vehicles: Optimal Action Filtering and Battery-in-the-Loop Validation
Despite the promising performance of deep reinforcement learning (DRL)-based energy management systems (EMSs) for electrified vehicles, persistent safety concerns regarding control actions hinder their real-world deployment. This article proposes a safe DRL-based EMS for hybrid electric vehicles (HEVs) that guarantee zero safety violations during both training and deployment. A model-based safety layer is developed with prior knowledge to filter unsafe actions with minimal disruption to agent exploration. This safety metric evaluation is embedded into the reward function via a Lagrangian relaxation (LR) method, enabling adaptive penalization of constraint violations and prompting efficient policy learning. A safe soft actor–critic (SSAC) EMS is then trained under stochastic conditions, including random initial battery state-of-charge (SOC) and multimodal driving cycles. The approach is validated through simulation and battery-in-the-loop (BIL) experiments. The proposed reward formulation accelerates safety-aware policy learning by 38.5% compared to conventional methods. In BIL tests, SSAC-EMS achieves over 95% fuel efficiency relative to the offline dynamic programming (DP) benchmark under unseen driving cycles and initial SOCs, with actions consistently respecting safety constraints. Compared to the adaptive equivalent consumption minimization strategy (AECMS), SSAC-EMS improves fuel economy by 6%–10% while delivering more stable SOC regulation and smoother engine operation.
- Open Access
- 29 January 2024
- Published by Elsevier in Renewable and Sustainable Energy Reviews
- Vol. 193
A review of the design process of energy management systems for dual-motor battery electric vehicles
- 29 January 2024
- Published by Elsevier in Renewable and Sustainable Energy Reviews
- Vol. 193
Open AccessA review of the design process of energy management systems for dual-motor battery electric vehicles
- 30 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 8 (2) , 2898-2914
Electrified Automotive Propulsion Systems: State-of-the-Art Review
The increase in pollution and carbon dioxide in the transportation sector motivates many countries to establish rules to reduce the emission and carbon footprint. The partial or total electrification of the automotive propulsion system is mandatory to minimize the impact of transportation on the environment. There are multiple possible architectures to electrify the vehicle propulsion system, with different degrees of electrification, and each of the architectures can provide a different balance between energy efficiency, vehicle performance, comfort, drivability, and safety. This article aims to present the definition of the automotive propulsion system electrification, the various degrees of electrification and operation modes, and the possible configurations of an electrified propulsion system by the electric machine position. This article also introduces the definition of the subsystems of the propulsion systems and their components, with an explanation of the subsystem and each of their parts. Based on the state-of-the-art technology development, it intends to present the industry’s common sense and knowledge on automotive propulsion system electrification and proposes a process to follow in the electrified propulsion system architecture selection.
- 30 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 8 (2) , 2898-2914
Electrified Automotive Propulsion Systems: State-of-the-Art Review
The increase in pollution and carbon dioxide in the transportation sector motivates many countries to establish rules to reduce the emission and carbon footprint. The partial or total electrification of the automotive propulsion system is mandatory to minimize the impact of transportation on the environment. There are multiple possible architectures to electrify the vehicle propulsion system, with different degrees of electrification, and each of the architectures can provide a different balance between energy efficiency, vehicle performance, comfort, drivability, and safety. This article aims to present the definition of the automotive propulsion system electrification, the various degrees of electrification and operation modes, and the possible configurations of an electrified propulsion system by the electric machine position. This article also introduces the definition of the subsystems of the propulsion systems and their components, with an explanation of the subsystem and each of their parts. Based on the state-of-the-art technology development, it intends to present the industry’s common sense and knowledge on automotive propulsion system electrification and proposes a process to follow in the electrified propulsion system architecture selection.
- Open Access
- 2 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Vehicular Technology
- Vol. 2, 419-435
Multi-Speed Gearboxes for Battery Electric Vehicles: Current Status and Future Trends
In the last decade, the automotive industry has undergone a paradigm shift towards electrification. Electric vehicles have become increasingly popular, but so far, they have almost solely utilized single-ratio gearboxes. The use of multiple gear ratios has several potential benefits, including enabling the electric traction machine and inverter to operate in a more efficient region, increasing vehicle acceleration, gradeability, and top speed, and reducing overall traction system mass and volume. Performance vehicles, light to heavy-duty trucks, and buses may especially benefit from multi-speed gearboxes due to their high torque and power requirements. This paper covers the fundamentals of applying multi-speed gearboxes to EVs, the latest designs, and future trends. The efforts of both academia and industry in this field are covered. A range of topics are discussed, including gearbox topologies, gear ratio selection, gearbox losses, noise vibration and harshness, gearbox control, shift scheduling, and regenerative braking. Prior studies are presented showing that depending on the drive cycle, vehicle type, and gearbox configuration, drivetrain energy consumption may be reduced slightly or increased anywhere from a few percent to thirty percent when utilizing a multi-speed configuration. While multi-speed EV traction systems do show considerable promise, more investigation is needed to conclusively determine in what cases they can outperform highly optimized single-speed systems.
- 2 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Vehicular Technology
- Vol. 2, 419-435
Open AccessMulti-Speed Gearboxes for Battery Electric Vehicles: Current Status and Future Trends
In the last decade, the automotive industry has undergone a paradigm shift towards electrification. Electric vehicles have become increasingly popular, but so far, they have almost solely utilized single-ratio gearboxes. The use of multiple gear ratios has several potential benefits, including enabling the electric traction machine and inverter to operate in a more efficient region, increasing vehicle acceleration, gradeability, and top speed, and reducing overall traction system mass and volume. Performance vehicles, light to heavy-duty trucks, and buses may especially benefit from multi-speed gearboxes due to their high torque and power requirements. This paper covers the fundamentals of applying multi-speed gearboxes to EVs, the latest designs, and future trends. The efforts of both academia and industry in this field are covered. A range of topics are discussed, including gearbox topologies, gear ratio selection, gearbox losses, noise vibration and harshness, gearbox control, shift scheduling, and regenerative braking. Prior studies are presented showing that depending on the drive cycle, vehicle type, and gearbox configuration, drivetrain energy consumption may be reduced slightly or increased anywhere from a few percent to thirty percent when utilizing a multi-speed configuration. While multi-speed EV traction systems do show considerable promise, more investigation is needed to conclusively determine in what cases they can outperform highly optimized single-speed systems.