Sadia Ali is a PhD candidate in Automotive Engineering for Intelligent Mobility at the University of Bologna, in collaboration with the University of Parma, specialising in data-driven modelling and State-of-Charge (SoC) estimation for energy storage systems. Her research applies machine learning techniques — reinforcement learning, LSTM neural networks, Gaussian Process Regression and gradient boosting — to lithium-ion batteries and hybrid supercapacitors, with particular expertise in signal analysis, CC-CV and Electrochemical Impedance Spectroscopy (EIS) based estimation methods, and real-time embedded deployment on STM32 microcontrollers and FPGA. She has a strong track record of translating advanced research into hardware-validated, real-time mobility and energy-storage solutions, with more than eight peer-reviewed publications, and brings over nine years of prior hands-on engineering experience in electrical systems, automation, control, laboratory testing and instrumentation. Her research areas include energy storage devices, battery management systems, electro-mobility, energy management, artificial intelligence, and control and optimisation.
Training
She is currently completing a PhD in Automotive Engineering for Intelligent Mobility at the University of Bologna and the University of Parma (2023–2026), in the field of energy systems, powertrains and vehicle performance. She holds a Master's degree in Electrical Engineering, with a specialisation in Automation and Control, from COMSATS University, Islamabad (2015–2018, final grade 3.71/4.0), with a thesis on the application of non-linear control techniques for the speed control of a three-phase induction motor. She earlier obtained a Bachelor's degree in Electrical Engineering from the University of Engineering and Technology, Taxila (2009–2013, final grade 3.61/4.0).
Professional experience
From 2014 to 2023 she worked as a Laboratory Engineer in the Department of Electrical and Computer Engineering at the International Islamic University, Islamabad. In this role she designed and conducted laboratory experiments across a wide range of modules, including power electronics, linear control systems, electrical machines, digital logic design, signals and systems, microcontrollers and microprocessors, and electronic circuit design, working with state-of-the-art laboratory equipment such as hardware-in-the-loop (HIL) benches (servomotor and ball-and-beam systems), PID control trainers and electrical machine trainers. She supervised interns in the hardware and software design of power-converter laboratory kits, including buck and boost converters, inverters and controlled rectifiers, and co-supervised undergraduate final-year projects.
Research activity
Since 2023 her doctoral research has focused on the state-of-charge estimation of energy storage systems. She has developed real-time SoC estimation frameworks for lithium-ion batteries and hybrid supercapacitors using Gaussian Process Regression, LSTM neural networks, reinforcement learning (TD3) and gradient-boosted (LSB) residual correction, incorporating single-point EIS measurements for fast in-situ estimation. She has deployed these frameworks on dual embedded targets, an STM32F411RE microcontroller and an Artix-7 FPGA (Nexys A7-100T), achieving microsecond-level inference suitable for low-cost automotive hardware, and has built full HDL pipelines in MATLAB HDL Coder, resolving fixed-point arithmetic and feedback-loop challenges for FPGA deployment. She has also conducted reinforcement-learning-based signal-to-noise ratio analysis for estimation robustness. Her earlier research includes non-linear and hybrid control strategies for induction motors, designed and simulated in MATLAB/Simulink. She has regularly participated in the IEEE International Workshop on Metrology for Automotive (2024–2026) and has organised technical seminars and workshops on smart grids, power electronics and electric-vehicle battery technologies.
Publications
S. Ali, V. Bianchi, G. Patrizi, L. Ciani, and I. De Munari, "State of Charge Estimation of Energy Storage Systems using a Flexible Reward based Reinforcement Learning Approach," accepted at the 20th IMEKO TC10 Conference, Lisbon, Portugal, 2026.
S. Ali, V. Bianchi, and I. De Munari, "Reinforcement Learning based State of Charge Estimation of a Lithium Ion Battery," IEEE International Workshop on Metrology for Automotive (MetroAutomotive), Brescia, Italy, 2026.
S. Ali, G. Patrizi, L. Ciani, I. De Munari, and V. Bianchi, "Signal-to-Noise Ratio Analysis for a Reinforcement Learning based State of Charge Estimation of a Hybrid Supercapacitor," IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 2026.
G. Patrizi, S. Ali, L. Ciani, F. Canzanella, I. De Munari, and V. Bianchi, "A Fast Approach for in situ SoC Estimation of a Supercapacitor based on Gaussian Process Regression and Electrochemical Impedance Spectroscopy," IEEE Transactions on Instrumentation and Measurement, 2026.
S. Ali, V. Bianchi, and I. De Munari, "A Microcontroller Based Optimized Framework for the State of Charge Estimation of a Lithium Ion Battery," IEEE International Workshop on Metrology for Automotive (MetroAutomotive), 2025.
V. Bianchi, F. Canzanella, S. Ali, I. De Munari, L. Ciani, and G. Patrizi, "A single-point EIS measurement for SOC estimation of supercapacitor," IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 2025.
S. Ali, M. Stighezza, G. Chiorboli, I. De Munari, and V. Bianchi, "An Optimized Long Short Term Memory and Gaussian Process Regression Based Framework for State of Charge Estimation," IEEE International Workshop on Metrology for Automotive (MetroAutomotive), 2024.
R. Afifa, S. Ali, M. Pervaiz, and J. Iqbal, "Adaptive Backstepping Integral Sliding Mode Control of a MIMO Separately Excited DC Motor," Robotics, vol. 12, no. 4, 2023.
S. Riaz, C.-W. Yin, R. Qi, B. Li, S. Ali, and K. Shehzad, "Design of Predefined Time Convergent Sliding Mode Control for a Nonlinear PMLM Position System," Electronics, vol. 12, no. 4, 2023.
S. Ali, A. Prado, and M. Pervaiz, "Hybrid Backstepping-Super Twisting Algorithm for Robust Speed Control of a Three-Phase Induction Motor," Electronics, vol. 12, no. 3, 2023.
Language skills
English: full professional proficiency (IELTS overall band C2, 8.5).
Technical and digital skills
Programming and modelling in MATLAB (proficient) and Python; embedded and hardware development on STM32F411RE microcontrollers and Artix-7 FPGA using Xilinx Vivado, HDL Coder, Embedded Coder and fixed-point arithmetic; circuit design and simulation tools (Proteus, Multisim, Mentor ModelSim); and CST Microwave Studio for antenna design.
Honours, awards and certifications
Professional certifications in "Electric Cars: Technology" (Delft University of Technology, 2023) and "Computing in Python" (Georgia Institute of Technology, 2021); third prize for undergraduate final-year project (University of Engineering and Technology, Taxila, 2013).
