Abstract
Engineering design has traditionally relied on expert knowledge, heuristics, and trial-and-error approaches. However, the rapid growth of data from sensors, simulations, and design software has paved the way for data-driven decision support in engineering design. Data-driven methods leverage statistical models, machine learning, and computational intelligence to assist engineers in making informed decisions, improving product quality, reducing design cycles, and optimizing resources. This paper provides a comprehensive review of data-driven decision support in engineering design, discussing methodologies, tools, applications, and challenges. Emphasis is placed on predictive modeling, optimization, and integration with computer-aided design (CAD) and manufacturing systems. Case studies demonstrate practical implementations, and potential future directions are outlined.
Keywords: Data-driven design, decision support system, engineering design, predictive modeling, optimization, machine learning, CAD integration
Full Issue
| View or download the full issue | PDF 98-111 |