Usaid Ahmad

Master Student at NUAA 

Office: A6203, Ming Forbidden City Campus, Nanjing University of Aeronautics and Astronautics

Phone: 025-84893599

Postal Code: 210016

Usaid Ahmad is a Master Student at the College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics (NUAA), Nanjing, China. He completed his Bachelor of Science in Mechanical Engineering from the University of Engineering and Technology, Lahore Pakistan. His work sits at the intersection of mechanical engineering and artificial intelligence, with a particular focus on intelligent condition monitoring, computer-vision–driven wear analysis, and the application of deep learning to real engineering problems.

He combines a strong mechanical engineering foundation with hands-on expertise in modern AI systems, having designed, trained, and deployed deep learning models for industrial and research applications. He is motivated, detail-oriented, and experienced in taking projects from research concept to working prototype.

•     Intelligent wear particle detection and characterization using deep learning

•     Instance segmentation with Mask R-CNN and multi-backbone architectures (ConvNeXt-V2, Swin Transformer) enhanced with CBAM attention

•     Ferrographic image analysis for machine health and fault diagnosis

•     Knowledge graphs (Neo4j) and Retrieval-Augmented Generation (RAG) for tribological diagnostics

•     Large Language Models (LLMs) for engineering decision support and automation

M.S. in Mechanical Engineering — Nanjing University of Aeronautics and Astronautics, Nanjing, China

B.S. in Mechanical Engineering — University of Engineering and Technology, Lahore, Pakistan

2021 – 2022 Mechanical Engineer / Technical Trainee — N.S Auto Industry, Lahore, Pakistan

•     Worked in the technical department supporting production, quality, and maintenance of automotive components.

•     Gained hands-on exposure to manufacturing processes, equipment monitoring, and shop-floor problem solving.

•     Intelligent ferrography framework (FMR-CNN): deep-learning wear particle analysis combining instance segmentation, knowledge graph, and RAG-based reasoning.

•     Deep Learning Specialization — DeepLearning.AI (Coursera)

•     Machine Learning — Stanford University / DeepLearning.AI (Coursera)

•     TensorFlow / PyTorch for Deep Learning

•     Generative AI and Large Language Models (LLMs)

•     Computer Vision with Deep Learning

Languages & Tools: Python, PyTorch, OpenCV, FastAPI, React, Neo4j, ChromaDB, Git

Areas: Deep Learning, Computer Vision, Instance Segmentation, LLMs & RAG, Knowledge Graphs, Data Visualization