With the surge of AI technologies reshaping our society in just the past few years, the engineering community is anxious to understand how these advancements will transform their workflows. Will AI-driven innovation come mainly from their software vendors, or do they also need to directly engage in its development and implementation? This webinar explores the latest developments in the AI-based design exploration technology captured in the OASIS.AI software to serve the needs of both software providers and end users.
The term “optimization” has seen a sharp resurgence in engineering media since the rise of tools like ChatGPT. However, for many, it still carries baggage from the 1990s, when limited computing resources and a lack of understanding led to unrealistic expectations and inconsistent and sometimes doubtful results. Optimization remains a technically demanding domain, requiring the handling of diverse variable types, high-dimensional design spaces, complex constraints, and multi-objective scenarios. While numerous algorithms have been developed over the years to address these challenges—often tailored to specific use cases—their sheer variety has created confusion about which methods to use, slowing widespread adoption.
After decades of research in AI-based learning algorithms, EmpowerOps has developed a comprehensive yet highly efficient automated exploration capability that is easy for users to adopt. In this presentation, EmpowerOps will discuss the latest advancements in its AI-based exploration engine, OASIS.AI, which extends traditional optimization paradigms into broader exploration, enabling engineers to evaluate “what if” scenarios and make use of historical data. This new AI approach efficiently handles highly complex scenarios, leveraging advanced search techniques and small data learning technologies refined over many years. Its robustness and efficiency have been validated across a wide range of benchmark cases, positioning it as a next-generation tool for optimization and exploration—ready to be embedded in OEM software through partnerships with EmpowerOps or directly utilized by end users.
Dr. Mike Sheh has held a variety of technical and management roles across the engineering and computing fields. He began his career as a CAE engineer at General Motors and later moved into the supercomputing sector, working as a specialist at Cray Research and SGI. His interest in engineering optimization led him to join Engineous Software, the developer of iSIGHT, one of the earliest commercial tools for Process Integration and Design Optimization (PIDO). Since then, he has actively advocated the application of optimization methods across a broad range of engineering and non-engineering domains.
In 2020, after leaving Dassault Systèmes, he participated in Empower Operations Corp. as Chief Strategist. In this role, he contributes to positioning the company’s AI-based exploration engine, OASIS.AI, with the goal of making next-generation exploration technologies more accessible and broadly adopted.
Across every industry, engineers face ever-shrinking time-to-market demands, often needing more time to optimize their designs fully. Traditional CAD and simulation tools fall short of enabling practical usage of optimization and generative design due to persistent bottlenecks in geometry regeneration, meshing, and long solve times. These limitations prevent engineers from fully leveraging the design space while meeting project timelines. In this presentation, we introduce a new paradigm in mechanical design optimization that integrates implicit modeling, meshless simulation methods, and machine learning to address these challenges. Through diverse use cases, we demonstrate how these techniques unlock the practical use of optimization while adhering to project timelines. Attendees will gain insights into the practical deployment of optimization workflows in industrial, fast-paced, multi-disciplinary settings.
Todd McDevitt is a seasoned product leader and engineering technologist with over 25 years of experience at the intersection of computational mechanics, simulation software, and advanced product design. As a Ph.D. in Mechanical Engineering and a licensed Professional Engineer, Todd has helped hundreds of companies across aerospace, automotive, high-tech, and energy sectors leverage simulation-driven workflows to accelerate innovation and improve product performance. Currently a Product Manager at nTopology, he leads efforts in applying AI and machine learning to next-generation engineering tools. Beyond his professional pursuits, Todd is an avid woodworker, machinist, fisherman, hockey player, and golfer—though his skills seem to decline roughly in that order.
*NOTE: When you register for one webinar, you will automatically be registered for both in this series.
