Supervisor: Assoc. Prof. Ir. Dr. Haslinda Bt Zabiri  (Chair, Chemical Engineering, UTP)
Co-Supervisor: Assoc. Prof. Dr. Syed Ali Ammar Taqvi 

Dr. Muhammad Shahid completed his Ph.D. (2022-2025) in Chemical Engineering at Universiti Teknologi PETRONAS (UTP), Malaysia. His doctoral research focused on integrating Artificial Intelligence with chemical engineering to enhance industrial monitoring and decision-making. He developed an Advisory Monitoring and Diagnostic Tool designed to track soft sensor performance in real time. The system can detect early degradation, segregate whether the issue originates from the process, sensors, or the model itself, and provide diagnostic insights for fault identification.

A key contribution of his work is the integration of root cause analysis and corrective action recommendations, enabling engineers to respond more effectively and maintain stable plant operation. During his Ph.D., he produced three high-impact Q1 journal publications and secured intellectual property for his algorithm.

Supervisor: Assoc. Prof. Dr. Syed Ali Ammar Taqvi 

Dr. Tuba Siraj Ansari completed her Ph.D. (2021-2025) in Chemical Engineering at NED University of Engineering and Technology, with a specialization in Intelligent Process Control. Her doctoral research focused on creating and applying advanced control methods for the Vinyl Chloride Monomer (VCM) distillation column by using system identification and Artificial Intelligence techniques. 

A significant contribution of her work lies in the stability analysis and performance comparison of conventional and AI-based controllers under setpoint tracking and disturbance rejection scenarios. Her research demonstrates improved robustness, enhanced control accuracy, and superior disturbance handling using intelligent control architectures. The outcomes of her work provide a systematic framework for implementing AI-driven control solutions in complex industrial separation processes. During her Ph.D., she produced two journal publications.

Dr. Nadia Khan completed her Ph.D. (2022-2025) with a specialization in Intelligent Fault Detection and Diagnosis in Process Systems. Her research focuses on developing advanced data-driven frameworks for fault detection, fault diagnosis, and multivariate time-series forecasting in complex industrial systems, particularly in Acid Gas Removal Units (AGRUs).

Her doctoral work integrates deep learning architectures, including LSTM, GRU, CNN-Transformer hybrid models, and Autoencoders for fault detection and predictive monitoring of nonlinear and complex process systems. A key aspect of her work is the integration of a hybrid CNN–Transformer–LSTM model for multivariate time-series forecasting, where predicted process dynamics are further utilized for robust fault detection and intelligent monitoring.

In addition to predictive modeling, her work emphasizes interpretability and transparency in industrial AI applications. She incorporates Explainable AI (XAI) techniques as an interpretability layer to translate complex model outputs into human-understandable insights for operators and decision-makers. Her research contributes toward improving process safety, reducing unplanned shutdowns, enabling predictive maintenance, and supporting digital transformation in the oil and gas sector.

Supervisor: Assoc. Prof. Dr. Syed Ali Ammar Taqvi 

Co-Supervisor: Dr. Syed Muhammad Bilal Kazmi 

Engr. Shazma Akram completed her Master’s (2025–26) in Chemical Engineering at NED University of Engineering & Technology, with a research focus on clean hydrogen production from biomass and waste resources. Her work integrates process simulation through Aspen Plus and data-driven modeling through Machine Learning (python) to optimize hydrogen yield and process performance. She developed and analyzed gasification-based flowsheets, performed sensitivity analysis on key operating variables temperature and feed/steam flow rates, and translated simulation outputs into predictive ML models for rapid screening of best-performing conditions. Her research contributes toward sustainable hydrogen pathways, supporting efficient conversion of locally available waste streams into low-carbon energy carriers.