Applied Sciences

Research

21 pages, 6327 KiB

Open AccessArticle

Environment Classification Using Machine Learning Methods for Eco-Driving Strategies in Intelligent Vehicles

by Jose del C. Julio-Rodríguez, Carlos A. Rojas-Ruiz, Alfredo Santana-Díaz, M. Rogelio Bustamante-Bello and Ricardo A. Ramirez-Mendoza

Appl. Sci. 2022, 12(11), 5578; https://doi.org/10.3390/app12115578 - 31 May 2022

Cited by 14 | Viewed by 2595

Abstract

This work presents the development of a classification method that can contribute to precise and increased awareness of the situational context of vehicles, for it to be used in autonomous driving applications. This work aims to obtain a method for machine-learning-based driving environment [...] Read more.

This work presents the development of a classification method that can contribute to precise and increased awareness of the situational context of vehicles, for it to be used in autonomous driving applications. This work aims to obtain a method for machine-learning-based driving environment classification that does not involve computer vision but instead makes use of dynamics variables from Inertial-Measurement-Unit (IMU) sensors and instantaneous energy consumption measurements. This article includes details about the data acquisition, the electric vehicle used for the experiments, and the pre-processing methods employed. This explores the viability of a method for classifying a vehicle’s driving environment. The results of such a system can potentially be used to provide precise information for path planning, energy optimization, or safety purposes. Information about the driving context could be also used to decide if the conditions are safe for autonomous driving or if human intervention is recommended or required. In this work, the feature selection process and statistical data pre-processing methods are evaluated. The pre-processed data are used to compare 13 different classification algorithms and then the best three are selected for further testing and data dimensionality reduction. Two approaches for feature selection based on feature importance and final classification scores are tested, achieving a classification mean accuracy of 93 percent with a real testing dataset that included three driving scenarios and eight different drivers. The obtained results and high classification accuracy represent a first approach for the further development of such classification systems and the potential for direct implementation into autonomous driving technology. Full article

(This article belongs to the Special Issue Frontiers in Mechatronics Systems for Automotive)

► Show Figures

Figure 1

23 pages, 23237 KiB

Open AccessArticle

Soft Passing over Traffic-Calming Devices by Controlled Suspension in Low-Speed Robotic Vehicles for Vulnerable People

by Ricardo Zavala-Yoé, Miguel Sandoval-Olivares, Luis Carlos Félix-Herrán and Ricardo A. Ramírez-Mendoza

Appl. Sci. 2022, 12(6), 3109; https://doi.org/10.3390/app12063109 - 18 Mar 2022

Viewed by 1967

Abstract

The usefulness of golf carts for transporting patients in hospital facilities is well known. Nursing homes, medical campuses, and any type of related service require the low-speed transport of patients either in a seat, in a wheelchair, or on a stretcher. This type [...] Read more.

The usefulness of golf carts for transporting patients in hospital facilities is well known. Nursing homes, medical campuses, and any type of related service require the low-speed transport of patients either in a seat, in a wheelchair, or on a stretcher. This type of transport is not limited to hospitals, but also includes other environments where there are people with special requirements. Think for instance of handicapped or elderly people that need a van because they have to go from their homes to any destination; therefore, the use of golf carts becomes relevant and attractive. Moreover, these carts could be automated for path following and deal with bumps, potholes, or sinkholes. In this context, the present research proposes a novel way to deal with this kind of road obstacle when the gentle transport of patients is a key element. In order to pass over these obstacles, a soft upwards displacement of the front and rear sections of the vehicle was achieved with magnetorheological dampers as part of the vehicle’s suspension system. In this way, people who need this gentle transport will not have any discomfort. Moreover, this work is aligned with the spirit of Automated Vehicles 3.0. Full article

(This article belongs to the Special Issue Frontiers in Mechatronics Systems for Automotive)

► Show Figures

Figure 1

14 pages, 4227 KiB

Open AccessArticle

Development of Optimization Based Control Strategy for P2 Hybrid Electric Vehicle including Transient Characteristics of Engine

by Gulnora Yakhshilikova, Sanjarbek Ruzimov, Ethelbert Ezemobi, Andrea Tonoli and Nicola Amati

Appl. Sci. 2022, 12(6), 2852; https://doi.org/10.3390/app12062852 - 10 Mar 2022

Cited by 8 | Viewed by 1926

Abstract

Models based on steady-state maps estimate fuel consumption to be 2–8% lower than real experimental measured values. This is due to the fact that during transient phases, the engine consumes more fuel than in steady phases. Some literature has addressed the conventional vehicle [...] Read more.

Models based on steady-state maps estimate fuel consumption to be 2–8% lower than real experimental measured values. This is due to the fact that during transient phases, the engine consumes more fuel than in steady phases. Some literature has addressed the conventional vehicle engine model that improves fuel consumption estimation’s accuracy during the transient state. However, the characteristics of the engine in the scope of hybrid electric vehicles (HEVs) with an integrated control strategy is yet to be covered. The controller is designed to minimize engine operation in the transient phase to enhance energy savings. In this paper, the correlation between fuel enrichment in transient and steady-state fuel estimation is established as transient correction factor (TCF). Its explanatory variable was the engine torque change rate. This paper describes the influence of engine transient characteristics on the fuel consumption of a mild HEV. The work attempts to improve the fuel economy of the HEV by introducing a penalty factor in the controller to optimize the use of the engine in transient regimes. A backward vehicle model was developed for a production vehicle with a conventional powertrain and validated experimentally using data available online. The corresponding hybrid vehicle model was developed by integrating the electric motor and battery components with the conventional vehicle model. A P2 off-axis configuration was chosen to this end as the HEV architecture. A conventional equivalent consumption minimization strategy (ECMS) was used to split the torque request between the engine and the electric motor. This control strategy was modified with TCF to penalize the engine torque change rate. The results of the simulation show that due to less transient operation of the engine, the fuel consumption was reduced from 923 g to 918 g under the US06 driving cycle. The fuel economy of the model has been simulated for UDDS and HW drive cycles too, and fuel consumption improved by 4.4 g and 3.2 g, respectively. It has been verified that by increasing the battery capacity twice (14s24p), the limitations imposed by the battery capacity can be minimized and the fuel usage can be reduced by 9 g in the UDDS cycle. Full article

(This article belongs to the Special Issue Frontiers in Mechatronics Systems for Automotive)

► Show Figures

Figure 1

23 pages, 9175 KiB

Open AccessArticle

Battery Sizing for Mild P2 HEVs Considering the Battery Pack Thermal Limitations

by Gulnora Yakhshilikova, Ethelbert Ezemobi, Sanjarbek Ruzimov and Andrea Tonoli

Appl. Sci. 2022, 12(1), 226; https://doi.org/10.3390/app12010226 - 27 Dec 2021

Cited by 8 | Viewed by 3337

Abstract

Small capacity and passively cooled battery packs are widely used in mild hybrid electric vehicles (MHEV). In this regard, continuous usage of electric traction could cause thermal runaway of the battery, reducing its life and increasing the risk of fire incidence. Hence, thermal [...] Read more.

Small capacity and passively cooled battery packs are widely used in mild hybrid electric vehicles (MHEV). In this regard, continuous usage of electric traction could cause thermal runaway of the battery, reducing its life and increasing the risk of fire incidence. Hence, thermal limitations on the battery could be implemented in a supervisory controller to avoid such risks. A vast literature on the topic shows that the problem of battery thermal runaway is solved by applying active cooling or by implementing penalty factors on electric energy utilization for large capacity battery packs. However, they do not address the problem in the case of passive cooled, small capacity battery packs. In this paper, an experimentally validated electro-thermal model of the battery pack is integrated with the hybrid electric vehicle simulator. A supervisory controller using the equivalent consumption minimization strategy with, and without, consideration of thermal limitations are discussed. The results of a simulation of an MHEV with a 0.9 kWh battery pack showed that the thermal limitations of the battery pack caused a 2–3% fuel consumption increase compared to the case without such limitations; however, the limitations led to battery temperatures as high as 180 °C. The same simulation showed that the adoption of a 1.8 kWh battery pack led to a fuel consumption reduction of 8–13% without thermal implications. Full article

(This article belongs to the Special Issue Frontiers in Mechatronics Systems for Automotive)

► Show Figures

Figure 1

15 pages, 3151 KiB

Open AccessArticle

Influence of the Final Ratio on the Consumption of an Electric Vehicle under Conditions of Standardized Driving Cycles

by David Sebastian Puma-Benavides, Javier Izquierdo-Reyes, Renato Galluzzi and Juan de Dios Calderon-Najera

Appl. Sci. 2021, 11(23), 11474; https://doi.org/10.3390/app112311474 - 3 Dec 2021

Cited by 8 | Viewed by 2556

Abstract

Electric vehicles must improve their electric drive system efficiency and effectively use their limited energy to become a viable means of transportation. As such, these technologies have undergone substantial improvements from their initial conception. More efficient powertrains, together with improved storage technologies, have [...] Read more.

Electric vehicles must improve their electric drive system efficiency and effectively use their limited energy to become a viable means of transportation. As such, these technologies have undergone substantial improvements from their initial conception. More efficient powertrains, together with improved storage technologies, have enabled more extended autonomy. However, from an engineering perspective, these systems are still a key area of research and optimization. This work presents a powertrain optimization methodology, developing energy savings and improving the performance of the electric vehicle by focusing on the differential. The proposed methodology includes a study of the dynamics of the electric vehicle and the generation of a mathematical model that represents it. By simulating the vehicle and varying the final ratio of the differential, a significant optimization for energy savings is obtained by developing a standardized driving cycle. In this case, NEDC, WLTC-2, and WLTC-3 test cycles are used. The results show that a short ratio improves performance, even if this implies a larger torque from the prime mover. Depending on the operating cycle used, an energy-saving between 3% and 8% was registered. An extended energy autonomy and an increment in the life-cycle of the batteries are expected in real driving scenarios. Full article

(This article belongs to the Special Issue Frontiers in Mechatronics Systems for Automotive)

► Show Figures

Figure 1

18 pages, 2340 KiB

Open AccessArticle

Parallel Hybrid Electric Vehicle Modelling and Model Predictive Control

by Trieu Minh Vu, Reza Moezzi, Jindrich Cyrus, Jaroslav Hlava and Michal Petru

Appl. Sci. 2021, 11(22), 10668; https://doi.org/10.3390/app112210668 - 12 Nov 2021

Cited by 15 | Viewed by 3822

Abstract

This paper presents the modelling and calculations for a hybrid electric vehicle (HEV) in parallel configuration, including a main electrical driving motor (EM), an internal combustion engine (ICE), and a starter/generator motor. The modelling equations of the HEV include vehicle acceleration and jerk, [...] Read more.

This paper presents the modelling and calculations for a hybrid electric vehicle (HEV) in parallel configuration, including a main electrical driving motor (EM), an internal combustion engine (ICE), and a starter/generator motor. The modelling equations of the HEV include vehicle acceleration and jerk, so that simulations can investigate the vehicle drivability and comfortability with different control parameters. A model predictive control (MPC) scheme with softened constraints for this HEV is developed. The new MPC with softened constraints shows its superiority over the MPC with hard constraints as it provides a faster setpoint tracking and smoother clutch engagement. The conversion of some hard constraints into softened constraints can improve the MPC stability and robustness. The MPC with softened constraints can maintain the system stability, while the MPC with hard constraints becomes unstable if some input constraints lead to the violation of output constraints. Full article

(This article belongs to the Special Issue Frontiers in Mechatronics Systems for Automotive)

► Show Figures

Figure 1

22 pages, 8522 KiB

Open AccessArticle

Processor-in-the-Loop Architecture Design and Experimental Validation for an Autonomous Racing Vehicle

by Eugenio Tramacere, Sara Luciani, Stefano Feraco, Angelo Bonfitto and Nicola Amati

Appl. Sci. 2021, 11(16), 7225; https://doi.org/10.3390/app11167225 - 5 Aug 2021

Cited by 12 | Viewed by 3015

Abstract

Self-driving vehicles have experienced an increase in research interest in the last decades. Nevertheless, fully autonomous vehicles are still far from being a common means of transport. This paper presents the design and experimental validation of a processor-in-the-loop (PIL) architecture for an autonomous [...] Read more.

Self-driving vehicles have experienced an increase in research interest in the last decades. Nevertheless, fully autonomous vehicles are still far from being a common means of transport. This paper presents the design and experimental validation of a processor-in-the-loop (PIL) architecture for an autonomous sports car. The considered vehicle is an all-wheel drive full-electric single-seater prototype. The retained PIL architecture includes all the modules required for autonomous driving at system level: environment perception, trajectory planning, and control. Specifically, the perception pipeline exploits obstacle detection algorithms based on Artificial Intelligence (AI), and the trajectory planning is based on a modified Rapidly-exploring Random Tree (RRT) algorithm based on Dubins curves, while the vehicle is controlled via a Model Predictive Control (MPC) strategy. The considered PIL layout is implemented firstly using a low-cost card-sized computer for fast code verification purposes. Furthermore, the proposed PIL architecture is compared in terms of performance to an alternative PIL using high-performance real-time target computing machine. Both PIL architectures exploit User Datagram Protocol (UDP) protocol to properly communicate with a personal computer. The latter PIL architecture is validated in real-time using experimental data. Moreover, they are also validated with respect to the general autonomous pipeline that runs in parallel on the personal computer during numerical simulation. Full article

(This article belongs to the Special Issue Frontiers in Mechatronics Systems for Automotive)

► Show Figures

Figure 1

16 pages, 7552 KiB

Open AccessArticle

Individual Drive-Wheel Energy Management for Rear-Traction Electric Vehicles with In-Wheel Motors

by Jose del C. Julio-Rodríguez, Alfredo Santana-Díaz. and Ricardo A. Ramirez-Mendoza

Appl. Sci. 2021, 11(10), 4679; https://doi.org/10.3390/app11104679 - 20 May 2021

Cited by 6 | Viewed by 3475

Abstract

In-wheel motor technology has reduced the number of components required in a vehicle’s power train system, but it has also led to several additional technological challenges. According to kinematic laws, during the turning maneuvers of a vehicle, the tires must turn at adequate [...] Read more.

In-wheel motor technology has reduced the number of components required in a vehicle’s power train system, but it has also led to several additional technological challenges. According to kinematic laws, during the turning maneuvers of a vehicle, the tires must turn at adequate rotational speeds to provide an instantaneous center of rotation. An Electronic Differential System (EDS) controlling these speeds is necessary to ensure speeds on the rear axle wheels, always guaranteeing a tractive effort to move the vehicle with the least possible energy. In this work, we present an EDS developed, implemented, and tested in a virtual environment using MATLAB™, with the proposed developments then implemented in a test car. Exhaustive experimental testing demonstrated that the proposed EDS design significantly improves the test vehicle’s longitudinal dynamics and energy consumption. This paper’s main contribution consists of designing an EDS for an in-wheel motor electric vehicle (IWMEV), with motors directly connected to the rear axle. The design demonstrated effective energy management, with savings of up to 21.4% over a vehicle without EDS, while at the same time improving longitudinal dynamic performance. Full article

(This article belongs to the Special Issue Frontiers in Mechatronics Systems for Automotive)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Frontiers in Mechatronics Systems for Automotive

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI