Yahia Mazzi

Verified @usmba.ac.ma

Faculty of Science and Technology of Fez, Sidi Mohamed Ben Abdellah University Fez, Morocco

Yahia Mazzi


            Download Compact PDF  
https://researchid.co/yahiamazzi

RESEARCH INTERESTS

battery management sytsem, electric vehicle, electric motor control, energy management system
8

Scopus Publications

213

Scholar Citations

5

Scholar h-index

5

Scholar i10-index

Scopus Publications

  • Speed Control of a PMSM Drive System Using a Nonsingular Terminal Sliding Mode Controller
    Statistics Optimization and Information Computing, 2025
  • A soft actor-critic reinforcement learning framework for optimal energy management in electric vehicles with hybrid storage
    Yahia Mazzi, Hicham Ben Sassi, Fatima Errahimi, Najia Es-Sbai
    Journal of Energy Storage, 2024
  • Lithium-ion battery state of health estimation using a hybrid model based on a convolutional neural network and bidirectional gated recurrent unit
    Yahia Mazzi, Hicham Ben Sassi, Fatima Errahimi
    Engineering Applications of Artificial Intelligence, 2024
  • Power transfer control within the framework of vehicle-to-house technology
    Hicham Ben Sassi, Yahia Mazzi, Fatima Errahimi, Najia Es-Sbai
    International Journal of Electrical and Computer Engineering, 2023
    <span lang="EN-US">The emerging vehicle-to-grid (V2G) technology has gained a lot of praise in the last few years, following its experimental validation in several countries. As a result, this technology is being investigated for standalone houses under the name of vehicle-to-house (V2H). This latter proposes a two-way power transfer between the electric vehicles and isolated houses relying on renewable sources for power supply. In this paper an implementation of the V2H technology is investigated, using the adaptive backstepping control approach for the bidirectional half-bridge and the integral sliding mode control for the DC-DC converter. The robustness of the controller and its capability to respond to the desired performances were tested using different realistic scenarios. The obtained results yielded, a perfect sinusoidal output voltage with a voltage level of 220 V and a frequency of 50 Hz. This is further been validated by a frequency analysis resulting in a THD of 0.25%.</span>
  • State of charge estimation of an electric vehicle's battery using tiny neural network embedded on small microcontroller units
    Yahia Mazzi, Hicham Ben Sassi, Ahmed Gaga, Fatima Errahimi
    International Journal of Energy Research, 2022
    The latest breakthroughs in artificial intelligence resulted in their adoption in the electric vehicle's battery management systems. Simultaneously, the remarkable increase in the number of embedded systems in electric vehicles (EVs) has led to the search for new optimized state of charge (SOC) estimation strategies suitable for implementation on small and limited MCUs. In this regard, this paper provides a design and quantization processes of the 1D convolutional neural network (1D CNN) and the GRU‐recurrent neural network (GRU‐RNN), devoted for SOC estimation. Both the NN algorithms are designed and trained using data collected from an 18650 Li‐ion battery. Furthermore, to account for the limited computational resources of the EV MCUs, the pre‐trained models are then converted into highly optimized C‐codes using the latest model quantification techniques. In this regard, this paper investigates, the performances of the STM32Cube.AI and the TensorFlow Lite for microcontroller (TFLite Micro), in quantizing the activation functions and weights of the proposed NN models. This is achieved by converting these latter from 32‐bits floating‐point to 8‐bit integer precision. The obtained experimental results, under different profiles, indicate that the 1D CNN is more accurate than the GRU‐based model with root mean squared error (RMSE) of 2.33% and mean absolute error (MAE) of 1.62%. Furthermore, the impact of the quantization using STM32Cube.AI is compared with that using the TFLite Micro. The obtained results, demonstrated the superiority of the 1D CNN model quantized using the STM32Cube.AI. This latter reduces the flash memory size of the 1D CNN model from 10.82 to 2.89 KB and the RAM size from 2.49 to 1.04 KB, compared to the TFLite Micro, which reduces the RAM size from 7.0107 to 4.23 KB, and the flash from 43.361 to 15.88 KB.
  • Processor in the loop implementation of state of charge estimation strategies for electric vehicle applications
    Hicham Ben Sassi, Yahia Mazzi, Fatima Errahimi, Najia Es-Sbai
    Lecture Notes in Electrical Engineering, 2021
  • Pil implementation of adaptive gain sliding mode observer and ann for soc estimation
    Yahia Mazzi, Hicham Ben Sassi, Fatima Errahimi, Najia Es-Sbai
    Lecture Notes in Networks and Systems, 2021
  • State of charge estimation using extended kalman filter
    Yahia Mazzi, Hicham Ben Sassi, Fatima Errahimi, Najia Es-Sbai
    2019 International Conference on Wireless Technologies Embedded and Intelligent Systems Wits 2019, 2019
    In a world where electric mobility is defining our way of living, electric storage is of great importance especially in applications such as electric vehicles. Although battery technologies are diverse, Lithium-ion technology dominates the market due to its high performance. However, in order to keep the security of this part, it is essential to use a battery management system (BMS) to ensure safe and optimum operation. As the key function of this system, accurate state of charge (SOC) estimation is crucial. In this paper, we propose an Extended Kalman Filter (EKF) for the state of charge estimation. Firstly, to achieve the best operation of the EKF an accurate model is required; in this work the first-order Thevenin is presented to model the behaviors of the battery. The internal parameters of the selected model are then identified using the least square algorithm. Simulation results of the model alongside the EKF algorithm for SOC estimation of 3.7V/2.6Ah capacity lithium battery are presented, followed by their implementation on electronic card, which consists of a PIC18F4550 microcontroller.

RECENT SCHOLAR PUBLICATIONS

  • Speed control of a PMSM drive system using a nonsingular terminal sliding mode controller
    Y Mazzi, HB Sassi, F Errahimi, N Es-Sbai
    Statistics, Optimization & Information Computing 13 (1), 450-458 , 2025
    2025.0
    Citations: 2
  • A soft actor-critic reinforcement learning framework for optimal energy management in electric vehicles with hybrid storage
    Y Mazzi, HB Sassi, F Errahimi, N Es-Sbai
    Journal of Energy Storage 99, 113344 , 2024
    2024.0
    Citations: 23
  • Lithium-ion battery state of health estimation using a hybrid model based on a convolutional neural network and bidirectional gated recurrent unit
    Y Mazzi, HB Sassi, F Errahimi
    Engineering Applications of Artificial Intelligence 127, 107199 , 2024
    2024.0
    Citations: 91
  • Power transfer control within the framework of vehicle-to-house technology
    HB Sassi, Y Mazzi, F Errahimi, N Es-Sbai
    International Journal of Electrical and Computer Engineering (IJECE) 13 (4 … , 2023
    2023.0
    Citations: 5
  • State of charge estimation of an electric vehicle's battery using tiny neural network embedded on small microcontroller units
    Y Mazzi, H Ben Sassi, A Gaga, F Errahimi
    International Journal of Energy Research 46 (6), 8102-8119 , 2022
    2022.0
    Citations: 53
  • Benchmarking and comparison of two open-source RTOSs for embedded systems based on ARM Cortex-M4 MCU
    Y Mazzi, A Gaga, F Errahimi
    Indian Journal of Science and Technology 14 (16), 1261-1273 , 2021
    2021.0
    Citations: 10
  • for Electric Vehicle Applications
    HB Sassi, Y Mazzi, F Errahimi, N Es-Sbai
    Proceedings of the 2nd International Conference on Electronic Engineering … , 2020
    2020.0
  • PIL Implementation of Adaptive Gain Sliding
    Y Mazzi, HB Sassi, F Errahimi
    Artificial Intelligence and Industrial Applications: Artificial Intelligence … , 2020
    2020.0
  • Processor in the Loop Implementation of State of Charge Estimation Strategies for Electric Vehicle Applications
    H Ben Sassi, Y Mazzi, F Errahimi, N Es-Sbai
    International Conference on Electronic Engineering and Renewable Energy, 495-501 , 2020
    2020.0
  • PIL implementation of adaptive gain sliding mode observer and ANN for SOC estimation
    Y Mazzi, H Ben Sassi, F Errahimi, N Es-Sbai
    International Conference on Artificial Intelligence & Industrial … , 2020
    2020.0
    Citations: 2
  • State of charge estimation using extended kalman filter
    Y Mazzi, HB Sassi, F Errahimi, N Es-Sbai
    2019 International Conference on Wireless Technologies, Embedded and … , 2019
    2019.0
    Citations: 27
  • Control of a Vehicle-to-Grid Charging Dtation with a Double Integral Sliding Mode Controller
    HBEN SASSI, Y MAZZI, F ERRAHIMI, N ES-SBAI, K LAHRECH
    Materials Research Proceedings 64 , 0

MOST CITED SCHOLAR PUBLICATIONS

  • Lithium-ion battery state of health estimation using a hybrid model based on a convolutional neural network and bidirectional gated recurrent unit
    Y Mazzi, HB Sassi, F Errahimi
    Engineering Applications of Artificial Intelligence 127, 107199 , 2024
    2024.0
    Citations: 91
  • State of charge estimation of an electric vehicle's battery using tiny neural network embedded on small microcontroller units
    Y Mazzi, H Ben Sassi, A Gaga, F Errahimi
    International Journal of Energy Research 46 (6), 8102-8119 , 2022
    2022.0
    Citations: 53
  • State of charge estimation using extended kalman filter
    Y Mazzi, HB Sassi, F Errahimi, N Es-Sbai
    2019 International Conference on Wireless Technologies, Embedded and … , 2019
    2019.0
    Citations: 27
  • A soft actor-critic reinforcement learning framework for optimal energy management in electric vehicles with hybrid storage
    Y Mazzi, HB Sassi, F Errahimi, N Es-Sbai
    Journal of Energy Storage 99, 113344 , 2024
    2024.0
    Citations: 23
  • Benchmarking and comparison of two open-source RTOSs for embedded systems based on ARM Cortex-M4 MCU
    Y Mazzi, A Gaga, F Errahimi
    Indian Journal of Science and Technology 14 (16), 1261-1273 , 2021
    2021.0
    Citations: 10
  • Power transfer control within the framework of vehicle-to-house technology
    HB Sassi, Y Mazzi, F Errahimi, N Es-Sbai
    International Journal of Electrical and Computer Engineering (IJECE) 13 (4 … , 2023
    2023.0
    Citations: 5
  • Speed control of a PMSM drive system using a nonsingular terminal sliding mode controller
    Y Mazzi, HB Sassi, F Errahimi, N Es-Sbai
    Statistics, Optimization & Information Computing 13 (1), 450-458 , 2025
    2025.0
    Citations: 2
  • PIL implementation of adaptive gain sliding mode observer and ANN for SOC estimation
    Y Mazzi, H Ben Sassi, F Errahimi, N Es-Sbai
    International Conference on Artificial Intelligence & Industrial … , 2020
    2020.0
    Citations: 2
  • for Electric Vehicle Applications
    HB Sassi, Y Mazzi, F Errahimi, N Es-Sbai
    Proceedings of the 2nd International Conference on Electronic Engineering … , 2020
    2020.0
  • PIL Implementation of Adaptive Gain Sliding
    Y Mazzi, HB Sassi, F Errahimi
    Artificial Intelligence and Industrial Applications: Artificial Intelligence … , 2020
    2020.0
  • Processor in the Loop Implementation of State of Charge Estimation Strategies for Electric Vehicle Applications
    H Ben Sassi, Y Mazzi, F Errahimi, N Es-Sbai
    International Conference on Electronic Engineering and Renewable Energy, 495-501 , 2020
    2020.0
  • Control of a Vehicle-to-Grid Charging Dtation with a Double Integral Sliding Mode Controller
    HBEN SASSI, Y MAZZI, F ERRAHIMI, N ES-SBAI, K LAHRECH
    Materials Research Proceedings 64 , 0