Juliano Pimentel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Juliano Pimentel has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
Alistair A. McEwan
University of Derby,School of Computing and Engineering,Derby,UK,DE22 1GB
3 shared publicationsHong Qing Yu
University of Derby,School of Computing and Engineering,Derby,UK,DE22 1GB
3 shared publications- Alistair A. McEwan
The University of Derby
2 shared publications - Hong Qing Yu
University of Derby
2 shared publications Jawad Arif
1 shared publicationTanya Vladimirova
1 shared publication
Latest Publications
- Open Access
- 31 July 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (15) , 8538
A Novel Real-Time Battery State Estimation Using Data-Driven Prognostics and Health Management
This paper presents a novel data-driven framework for real-time State of Charge (SOC) estimation in lithium-ion battery systems using a data-driven Prognostics and Health Management (PHM) approach. The method leverages an optimized bidirectional Long Short-Term Memory (Bi-LSTM) network, trained with enhanced datasets filtered via exponentially weighted moving averages (EWMAs) and refined through SHAP-based feature attribution. Compared against a Extended Kalman Filter (EKF) and Unscented Kalman Filter (UKF) across ten diverse drive cycles, the proposed model consistently achieved superior performance, with mean absolute errors (MAEs) as low as 0.40%, outperforming EKF (0.66%) and UKF (1.36%). The Bi-LSTM model also demonstrated higher R2 values (up to 0.9999) and narrower 95% confidence intervals, confirming its precision and robustness. Real-time implementation on embedded platforms yielded inference times of 1.3–2.2 s, validating its deployability for edge applications. The framework’s model-free nature makes it adaptable to other nonlinear, time-dependent systems beyond battery SOC estimation.
- 31 July 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (15) , 8538
Open AccessA Novel Real-Time Battery State Estimation Using Data-Driven Prognostics and Health Management
This paper presents a novel data-driven framework for real-time State of Charge (SOC) estimation in lithium-ion battery systems using a data-driven Prognostics and Health Management (PHM) approach. The method leverages an optimized bidirectional Long Short-Term Memory (Bi-LSTM) network, trained with enhanced datasets filtered via exponentially weighted moving averages (EWMAs) and refined through SHAP-based feature attribution. Compared against a Extended Kalman Filter (EKF) and Unscented Kalman Filter (UKF) across ten diverse drive cycles, the proposed model consistently achieved superior performance, with mean absolute errors (MAEs) as low as 0.40%, outperforming EKF (0.66%) and UKF (1.36%). The Bi-LSTM model also demonstrated higher R2 values (up to 0.9999) and narrower 95% confidence intervals, confirming its precision and robustness. Real-time implementation on embedded platforms yielded inference times of 1.3–2.2 s, validating its deployability for edge applications. The framework’s model-free nature makes it adaptable to other nonlinear, time-dependent systems beyond battery SOC estimation.
- Open Access
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 104-109
Multi-Step Ahead Battery SOC Estimation Using Data-Driven Prognostics and Health Management
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 104-109
Open AccessMulti-Step Ahead Battery SOC Estimation Using Data-Driven Prognostics and Health Management
- 1 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1954-1959
A Comprehensive Machine Learning Methodology for Embedded Systems PHM
Techniques of Machine Learning (ML) have recently been widely used in several applications, but not much for embedded systems, particularly those of safety-critical functionality, and are expected to help solve complex PHM and RUL which are difficult to be overcome with traditional approaches. This paper proposes a novel approach to encompass data-driven system-level health management, which comprises three main processes: an exhaustive offline training using machine learning techniques to derive a model capable of predicting the system of interest within fixed performance criteria; followed by its deployment on the targeted embedded system for real-time health assessment and finally the ability to provide a multi-step ahead forecasting for the system prognostics.The ability to monitor the current state of the systems and predict their behaviour becomes essential. Therefore, techniques to establish fault tolerance and fault prediction are required. Condition monitoring (CM), prognostics and health management (PHM) and remaining useful life (RUL) are enablers for fault detection, fault progression and system degradation.This paper presents a ML-based methodology for the PHM of embedded systems, aiming at generalization and real-time performance.
- 1 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1954-1959
A Comprehensive Machine Learning Methodology for Embedded Systems PHM
Techniques of Machine Learning (ML) have recently been widely used in several applications, but not much for embedded systems, particularly those of safety-critical functionality, and are expected to help solve complex PHM and RUL which are difficult to be overcome with traditional approaches. This paper proposes a novel approach to encompass data-driven system-level health management, which comprises three main processes: an exhaustive offline training using machine learning techniques to derive a model capable of predicting the system of interest within fixed performance criteria; followed by its deployment on the targeted embedded system for real-time health assessment and finally the ability to provide a multi-step ahead forecasting for the system prognostics.The ability to monitor the current state of the systems and predict their behaviour becomes essential. Therefore, techniques to establish fault tolerance and fault prediction are required. Condition monitoring (CM), prognostics and health management (PHM) and remaining useful life (RUL) are enablers for fault detection, fault progression and system degradation.This paper presents a ML-based methodology for the PHM of embedded systems, aiming at generalization and real-time performance.
- 6 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 309-316
A Novel Real-Time Framework for Embedded Systems Health Monitoring
This paper proposes a real-time framework, used as a multi-step ahead forecasting system that can be used for prognostics and health management (PHM), aiming to address a number of industrial-scaled embedded systems where failures can lead to catastrophic events. A novel framework is presented, which combines strong offline training using machine learning techniques with online multi-step forecasting for realtime condition monitoring and prognostics. The offline training is performed with the objective to derive a model capable of predicting the system of interest within fixed performance criteria, which are the metrics that provided the best accuracy and the estimated prediction time to anticipate the performance in real-time. The online inference, on the other hand, uses techniques of multi-step forecasting to provide an advisory window for the operator in case one or multiple faults lead the system for a non-operational state or a hazardous situation. This paper propositions are tested and validated on a real system dataset, where frequent faults were detected during a certain period of time. Dimensionality reduction techniques were initially used on the dataset, ensuring that the overall model accuracy was not impaired, then an optimized bidirectional long short-term memory (LSTM) model was chosen due to its inherent capacity to solve the issue of vanishing gradients for time-dependent and sequential data series. The optimized model is then flashed on two target microcontrollers, which continuously refresh data received from the sensors and actuators in the field. The proposed framework was compared with other strategies, tested and validated on a real application case.
- 6 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 309-316
A Novel Real-Time Framework for Embedded Systems Health Monitoring
This paper proposes a real-time framework, used as a multi-step ahead forecasting system that can be used for prognostics and health management (PHM), aiming to address a number of industrial-scaled embedded systems where failures can lead to catastrophic events. A novel framework is presented, which combines strong offline training using machine learning techniques with online multi-step forecasting for realtime condition monitoring and prognostics. The offline training is performed with the objective to derive a model capable of predicting the system of interest within fixed performance criteria, which are the metrics that provided the best accuracy and the estimated prediction time to anticipate the performance in real-time. The online inference, on the other hand, uses techniques of multi-step forecasting to provide an advisory window for the operator in case one or multiple faults lead the system for a non-operational state or a hazardous situation. This paper propositions are tested and validated on a real system dataset, where frequent faults were detected during a certain period of time. Dimensionality reduction techniques were initially used on the dataset, ensuring that the overall model accuracy was not impaired, then an optimized bidirectional long short-term memory (LSTM) model was chosen due to its inherent capacity to solve the issue of vanishing gradients for time-dependent and sequential data series. The optimized model is then flashed on two target microcontrollers, which continuously refresh data received from the sensors and actuators in the field. The proposed framework was compared with other strategies, tested and validated on a real application case.
- 1 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 696-703
Towards a Real-Time Smart Prognostics and Health Management (PHM) of Safety Critical Embedded Systems
Machine learning techniques for the prognostics and health management of safety critical embedded systems is an area that has raised an increased interest recently. This paper investigates an implementable machine learning pipeline to address PHM requirements. Different types of machine learning techniques are evaluated on a real case study considering accuracy and real-time effectiveness. The referred system exhibited abnormal behaviour with multiple faults during an observed period, which led it to a low system availability and required maintenance, disturbing the normal operation. This paper presents a system approach to the fault finding, aiming its use in real-time applications. We started with a thorough review of the available features, followed by a consistent hyperparameters optimization across all different techniques, ensuring a comparable baseline. Finally, the results were compared according to a defined evaluation and performance criteria, using a) metrics such as mean square error and R-squared to determine how well the model fitted the dataset, and b) execution times for their fit and predict methods for different training and test sizes, to anticipate their performance on real-time applications. All models presented a very good result to predict the output state of the system, but the stacked models outperformed the remaining ones. The proposed framework has been tested and validated on a real application case.
- 1 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 696-703
Towards a Real-Time Smart Prognostics and Health Management (PHM) of Safety Critical Embedded Systems
Machine learning techniques for the prognostics and health management of safety critical embedded systems is an area that has raised an increased interest recently. This paper investigates an implementable machine learning pipeline to address PHM requirements. Different types of machine learning techniques are evaluated on a real case study considering accuracy and real-time effectiveness. The referred system exhibited abnormal behaviour with multiple faults during an observed period, which led it to a low system availability and required maintenance, disturbing the normal operation. This paper presents a system approach to the fault finding, aiming its use in real-time applications. We started with a thorough review of the available features, followed by a consistent hyperparameters optimization across all different techniques, ensuring a comparable baseline. Finally, the results were compared according to a defined evaluation and performance criteria, using a) metrics such as mean square error and R-squared to determine how well the model fitted the dataset, and b) execution times for their fit and predict methods for different training and test sizes, to anticipate their performance on real-time applications. All models presented a very good result to predict the output state of the system, but the stacked models outperformed the remaining ones. The proposed framework has been tested and validated on a real application case.