Professor
Call: +34 976 761 927
Email: antoniob@unizar.es
Address: Dpto. IEC, Edif. Ada Byron, C/ María de Luna, 1 50018 (Zaragoza, Spain)
ABOUT ME
Antonio Bono ha desarrollado su carrera investigadora en el contexto de sistemas de machine learning implementados en dispositivos electrónicos.
Obtuvo el título de Ingeniero Técnico en Electrónica Industrial en 1995 para después entrar a trabajar como diseñador hardware/software en el departamento de I+D de la empresa Teltronic S.A.U. donde estuvo 4 años y 7 meses.
En el año 2001 entro como profesor interino a tiempo completo en la Universidad de Zaragoza con responsabilidad docente desde el primer día en la asignatura troncal obligatoria Sistemas electrónicos basados en microprocesadores e Instrumentación Electrónica, a la vez que siguió formándose en Ingeniería Industrial.
En 2006 concursó y obtuvo la plaza de profesor colaborador (contratado laboral a tiempo completo indefinido).
En 2008 obtuvo el título de Ingeniero Industrial con la mención de Electrónica Industrial.
En 2016 obtuvo el título de doctor en el programa de Tecnología Electrónica.
En 2019 transformó su plaza a profesor contratado doctor, donde continúa actualmente trabajando en la Escuela de Ingeniería y Arquitectura.
Entre 2001 y 2016 colaboró estrechamente y perteneció a los grupos Tecnodiscap y CVLab colaboró aplicando técnicas de machine learning en diversos proyectos, entre los que destacan varios proyectos europeos asociados a la medición y mejora de la calidad de vida en ancianos y personas con discapacidad en sus hogares y otros centros.
En 2017 se incorporó al grupo de HowLAB donde ha trabajado, entre otros, aplicando machine learning a proyectos que incluyen sistemas de gestión de energía, lo que incluye modelado de baterías, estimación de degradación y sistemas de predicción de caídas en instalaciones offgrid (donde ha sido Investigador Principal).
Los méritos personales más destacados incluyen:
- 10 publicaciones en revistas indexadas, 2 lecture notes y 35 comunicaciones a congresos. Publicación en revistas relevantes, tales como IEEE Transactions on Industrial Electronics, Energies, Journal of Power Sources, IEEE Sensors Journal, Neural Computing and Applications y Journal of Ambient Intelligence and Smart Environments.
- En cuanto a los proyectos de investigación ha sido el investigador principal de un proyecto y colaborador en 19 proyectos que incluyen tanto financiación pública como privada, así como nacional e internacional.
- Derivado de la investigación llevada a cabo en colaboración con empresas privadas es co-inventor en 2 patentes, una con BSH Electrodomésticos.
PUBLICATIONS
2021
Sanz-Gorrachategui, Iván; Pastor-Flores, Pablo; Pajovic, Milutin; Wang, Ye; Orlik, Philip V; Bernal-Ruiz, Carlos; Bono, Antonio; Artal-Sevil, Jesús Sergio
Remaining Useful Life Estimation for LFP Cells in Second-Life Applications Journal Article
In: IEEE Transactions on Instrumentation and Measurement, vol. 70, pp. 1-10, 2021, ISSN: 1557-9662.
@article{9343322,
title = {Remaining Useful Life Estimation for LFP Cells in Second-Life Applications},
author = {Iván Sanz-Gorrachategui and Pablo Pastor-Flores and Milutin Pajovic and Ye Wang and Philip V Orlik and Carlos Bernal-Ruiz and Antonio Bono and Jesús Sergio Artal-Sevil},
doi = {10.1109/TIM.2021.3055791},
issn = {1557-9662},
year = {2021},
date = {2021-01-01},
journal = {IEEE Transactions on Instrumentation and Measurement},
volume = {70},
pages = {1-10},
abstract = {The increasing deployment of battery storage applications in both grid storage and electric vehicle fields is generating a vast used battery market. These batteries are typically recycled but could be reused in second-life applications. One of the challenges is to obtain an accurate remaining useful life (RUL) estimation algorithm, which determines whether a battery is suitable for reuse and estimates the number of second-life cycles the battery will last. In this article, the RUL estimation problem is considered. We propose several health indicators (HIs), some of which have not been explored before, along with simple yet effective estimation and classification algorithms. These algorithms include classification techniques such as regularized logistic regression (RLR), and regression techniques such as multivariable linear regression (MLR) and multilayer perceptron (MLP). As a more advanced solution, a multiple expert system combining said techniques is proposed. The performance of the algorithms and features is evaluated on a recent lithium iron phosphate (LFP) data set from Toyota Research Institute. We obtain satisfactory results in the estimation of RUL cycles with errors down to 49 root mean square error (RMSE) cycles for cells that live up to 1200 cycles, and 0.24% mean relative error (MRE) for the prediction of the evolution of capacity.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2020
Guillén-Asensio, A; Sanz-Gorrachategui, I; Pastor-Flores, P; Artal-Sevil, J S; Bono, Antonio; Brío, Bonifacio Martín; Bernal-Ruiz, C
Battery state prediction in photovoltaic standalone installations Proceedings Article
In: 2020 Fifteenth International Conference on Ecological Vehicles and Renewable Energies (EVER), pp. 1-6, 2020.
@inproceedings{9243111,
title = {Battery state prediction in photovoltaic standalone installations},
author = {A Guillén-Asensio and I Sanz-Gorrachategui and P Pastor-Flores and J S Artal-Sevil and Antonio Bono and Bonifacio Martín Brío and C Bernal-Ruiz},
doi = {10.1109/EVER48776.2020.9243111},
year = {2020},
date = {2020-09-01},
booktitle = {2020 Fifteenth International Conference on Ecological Vehicles and Renewable Energies (EVER)},
pages = {1-6},
abstract = {Effective energy treatment is one of the challenges to which scientists are devoting more interest and resources. Currently, there is a need to optimize the generation of energy by renewable methods and to improve the storage and management of battery cells. One of these emerging lines aims to face the problem of uncertainty that exists in the generation of energy in photovoltaic installations. In this paper, we proposed to use machine learning methods to predict the state (voltage) of the batteries at several days into the future. The results obtained from two recurrent neural networks such as NARX and LSTM are compared, getting good results with both. Two approaches are considered: sample-based prediction and pattern-based forecasting.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Artal-Sevil, J S; Sanz-Gorrachategui, I; Pastor, P; Bernal-Ruiz, C; Perez-Cebolla, F J; Bono, Antonio
New Smart Control based on MPPT/MEPT Algorithm for Hybrid Fuel Cell Power System Proceedings Article
In: 2020 Fifteenth International Conference on Ecological Vehicles and Renewable Energies (EVER), pp. 1-10, 2020.
@inproceedings{9243139,
title = {New Smart Control based on MPPT/MEPT Algorithm for Hybrid Fuel Cell Power System},
author = {J S Artal-Sevil and I Sanz-Gorrachategui and P Pastor and C Bernal-Ruiz and F J Perez-Cebolla and Antonio Bono},
doi = {10.1109/EVER48776.2020.9243139},
year = {2020},
date = {2020-09-01},
booktitle = {2020 Fifteenth International Conference on Ecological Vehicles and Renewable Energies (EVER)},
pages = {1-10},
abstract = {In this paper, a new algorithm for enhanced management of a hybrid fuel-cell system is proposed. The purpose of this algorithm, which has been called Maximum Efficiency Point Tracking algorithm (MEPT-algorithm), is to polarize the fuel cell in an optimum point maximizing its efficiency and minimizing the fuel consumption. The goal is to guarantee fast power transients in the load while the fuel cell is kept in the optimum point by the hybridization of a fuel cell with an energy storage system (ESS) based on ultracapacitors. The hybrid power system model has been simulated in Matlab/Simulink applying the proposed algorithm and the classical Maximum Power Point Tracking (MPPT) algorithm. The combined control in DC/DC converters allows us to modify the Fuel Cell's operating point, as well as its MPPT or MEPT algorithm. A detailed analysis of the results verifies the benefits of the use of MEPT vs only the MPPT. Typical figures of merit and conclusions are also presented in this paper.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Artal-Sevil, J S; Bernal-Ruiz, C; Bono, Antonio; Peñas, Santos M
Design of a Fuzzy-Controller for a Magnetic Levitation System using Hall-Effect sensors Proceedings Article
In: 2020 XIV Technologies Applied to Electronics Teaching Conference (TAEE), pp. 1-9, 2020.
@inproceedings{9163711,
title = {Design of a Fuzzy-Controller for a Magnetic Levitation System using Hall-Effect sensors},
author = {J S Artal-Sevil and C Bernal-Ruiz and Antonio Bono and Santos M Peñas},
doi = {10.1109/TAEE46915.2020.9163711},
year = {2020},
date = {2020-07-01},
booktitle = {2020 XIV Technologies Applied to Electronics Teaching Conference (TAEE)},
pages = {1-9},
abstract = {This paper shows the implementation of Fuzzy Control techniques on a small Magnetic Levitation system. The analyzed application is a study problem of a non-linear and unstable system. Fuzzy control is an appropriate alternative for those cases where modelling the system is complicated, mainly due to the mathematical complexity of the model. The advantage of Fuzzy techniques is that any additional adjustment in the system only requires modifying the different fuzzy rules implemented, instead of redesigning the entire associated controller again. The control implemented here is made up of two feedback loops (position and current variables). A Hall sensor has been used to determine the position of the sphere to be levitated. Matlab/Simulink has been the software used for the development of the model and its simulation. In this way, the dynamic response of the system has been studied. The results and the different figures of merit obtained are shown by simulating the model presented. The initial objectives have been satisfactorily achieved.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2019
Pastor-Flores, Pablo; Bernal-Ruiz, Carlos; Sanz-Gorrachategui, Iván; Bono, Antonio; Brío, Bonifacio Martín; Artal-Sevil, Jesús Sergio; Perez-Cebolla, Francisco J
Analysis of Li-ion battery degradation using self-organizing maps Proceedings Article
In: IECON 2019 – 45th Annual Conference of the IEEE Industrial Electronics Society, pp. 4525-4530, 2019, ISSN: 2577-1647.
@inproceedings{8926907,
title = {Analysis of Li-ion battery degradation using self-organizing maps},
author = {Pablo Pastor-Flores and Carlos Bernal-Ruiz and Iván Sanz-Gorrachategui and Antonio Bono and Bonifacio Martín Brío and Jesús Sergio Artal-Sevil and Francisco J Perez-Cebolla},
doi = {10.1109/IECON.2019.8926907},
issn = {2577-1647},
year = {2019},
date = {2019-10-01},
booktitle = {IECON 2019 - 45th Annual Conference of the IEEE Industrial Electronics Society},
volume = {1},
pages = {4525-4530},
abstract = {This paper proposes a new methodology to identify the different degradation processes of Li-Ion battery cells. The goal of this study is to determine if different degradation factors can be separated by waveform analysis from aged cells with similar remaining capacity. In contrast to other works, the proposed method identifies the past operating conditions in the cell, regardless of the actual State of Health. The methodology is based on a data-driven approach by using a SOM (Self-organizing map), an unsupervised neural network. To verify the hypothesis a SOM has been trained with laboratory data from whole data cycles, to classify cells concerning their degradation path and according to their discharge voltage patterns. Additionally, this new methodology based on the SOM allows discriminating groups of cells with different cycling conditions (based on depth of discharge, ambient temperature and discharge current). This research line is very promising for classification of used cells, not only depending on their current static parameters (capacity, impedance), but also the battery use in their past life. This will allow making predictions of the Remaining Useful Life (RUL) of a battery with greater precision.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}