Authors: Anil Verma, Sneha R. Tiwari, Mohammad Irfan Shaikh, Pooja Srivastav, Shyam prasas
Abstract: In recent years, data-driven modelling has become a central paradigm in engineering analysis and design due to the rapid growth of sensing technologies, computational power, and availability of large-scale datasets. Quantitative methods play a crucial role in transforming raw engineering data into meaningful models that can describe, predict, and optimize system behavior. This paper presents a comprehensive review of quantitative methods used in data-driven modelling for engineering applications. Classical statistical techniques, regression-based models, numerical optimization, and modern machine learning approaches are discussed in detail. The integration of datadriven models with physical knowledge and engineering constraints is emphasized, highlighting hybrid and physics-informed approaches. The paper also reviews common engineering applications such as structural health monitoring, manufacturing process optimization, energy systems, and control engineering. Challenges related to data quality, model interpretability, uncertainty, and scalability are critically analyzed. Finally, future research directions are outlined, focusing on robust, explainable, and computationally efficient quantitative modelling frameworks. The review aims to provide a structured understanding for researchers and practitioners working at the intersection of data science and engineering systems.
Keywords: Data-driven modelling; quantitative methods; engineering systems; regression analysis; machine learning; uncertainty quantification; optimization
Full Issue
| View or download the full issue | PDF 89-101 |