Experimentation and Validation of Analytical Modeling and Finite Element Simulation of Different Metal Sheets Using Incremental Sheet Forming (ISF) /

By Pasha, Muhammad Taqveem Ahsan . . 52p. , An ever increasing demand of manufactured products calls for new manufacturing techniques that are cost effective and efficient. The global population is at an unprecedented rise and anticipating an increased demand for efficient, cheap and durable vehicles as well as automobile parts is nothing but obvious. With a population of over 216 million people, Pakistan stands 5thin the global ranking population wise. The population boom in Pakistan is growing at the rate of about 1.8pc a year, which, when extrapolated to the year 2030, brings out a staggering figure of 240 million people. With little growth in the industrial sector of Pakistan, the local market is forced to import goods for the Pakistani consumer. This presents the businesses and manufacturers all over the world a great opportunity to attract a huge mass of potential buyers in the Pakistani market. However, being a struggling economy, the import culture immensely upsets the balance of imports and exports of Pakistan. The purpose of this research is to promote a cost effective means of manufacturing for the local firms in order to counter the huge influx of imports. Novel techniques will not only promote the culture of research and development in the country, but will also enable the local manufacturers to explore options to fulfil the demand in the local market and provide opportunities for indigenous talent to play their part in the economic development of the nation. Single Point Incremental Forming (SPIF) is a relatively new technique of sheet metal forming. It is a die-less process that shapes the metal sheet in incremental steps for precision and accuracy. The process is relatively simple; a tool path is generated in accordance with the CAD model, the metal sheet is subjected to forming force via computer numeric controlled tool in presence of a lubricant. Once the tool completes its path, the sheet is formed in the desired shape. The materials used in this research are procured from the local market of Pakistan, hence suggesting the automakers over here to try new lines of manufacturing that uses indigenous materials to minimize imports. This study is based on the incremental formability of two materials; Al 5083 and Low Carbon Steel (0.04% Carbon). Both materials are readily available in the local market. The research targets the results of ABAQUS simulations run on the aforementioned materials to experimentally verify them and see their applicability on the practical sid. 30cm.

Place Hold on Experimentation and Validation of Analytical Modeling and Finite Element Simulation of Different Metal Sheets Using Incremental Sheet Forming (ISF) /

Comparison of Different Machine Learning Models for Quality Control in Biscuit Manufacturing Industry of Pakistan /

By Awais, Muhammad . . 113p. , Ensuring consistent product quality is a critical challenge in the biscuit manufacturing industry, particularly in developing economies like Pakistan, where manual inspection remains the norm. This approach, however, is prone to human error, fatigue, and inconsistency, leading to variable quality control outcomes. This research proposes an intelligent, machine learning–based automated quality inspection system tailored for real-world biscuit production lines. A comprehensive dataset of 40,000 high-resolution images was curated, representing four popular biscuit varieties Rio, Sooper, Candy, and Marie captured under actual factory lighting conditions. The dataset includes both defective and non-defective samples, covering a wide range of defect types such as breakage, charring, deformation, and missing pieces. To ensure high-quality annotations with scalable efficiency, a semi-automated iterative annotation framework was developed, combining initial manual labeling with model-assisted annotation and human-in-the-loop refinement across multiple cycles. Multiple state-ofthe-art machine learning models were implemented, fine-tuned, and rigorously evaluated, including YOLOv8, YOLOv11, YOLOv12, Faster R-CNN (via Detectron2), and Vision Transformer (ViT-B/16). Models were assessed using key performance metrics such as mAP@0.5:0.95, precision, recall, F1-score, inference speed (FPS), and computational efficiency. The results demonstrate that modern deep learning models, particularly YOLOv12 and Vision Transformers, achieve high detection accuracy (mAP > 90%) while maintaining feasibility for real-time deployment when optimized. This study provides a comparative analysis of accuracy-speed trade-offs, offering actionable insights for manufacturers seeking cost-effective, scalable solutions. The research concludes with practical recommendations for integrating AI-driven inspection systems into existing production infrastructure in resource-constrained environments, balancing performance, hardware requirements, and long-term maintainability. 30cm.

Place Hold on Comparison of Different Machine Learning Models for Quality Control in Biscuit Manufacturing Industry of Pakistan /

NUST Institutions Library Catalogue Search for 'kw,wrdl: su-br:au:"Supervisor: Dr. Muhammad Shahid"'

Experimentation and Validation of Analytical Modeling and Finite Element Simulation of Different Metal Sheets Using Incremental Sheet Forming (ISF) /

Comparison of Different Machine Learning Models for Quality Control in Biscuit Manufacturing Industry of Pakistan /