Search for: All records

Aerodynamic shape optimization is very useful for enhancing the performance of wind-sensitive structures. However, shape parameterization, as the first step in the pipeline of aerodynamic shape optimization, still heavily depends on empirical judgment. If not done properly, the resulting small design space may fail to cover many promising shapes, and hence hinder realizing the full potential of aerodynamic shape optimization. To this end, developing a novel shape parameterization scheme that can reflect real-world complexities while being simple enough for the subsequent optimization process is important. This study proposes a machine learning-based scheme that can automatically learn a low-dimensional latent representation of complex aerodynamic shapes for bluff-body wind-sensitive structures. The resulting latent representation (as design variables for aerodynamic shape optimization) is composed of both discrete and continuous variables, which are embedded in a hierarchy structure. In addition to being intuitive and interpretable, the mixed discrete and continuous variables with the hierarchy structure allow stakeholders to narrow the search space selectively based on their interests. As a proof-of-concept study, shape parameterization examples of tall building cross sections are used to demonstrate the promising features of the proposed scheme and guide future investigations on data-driven parameterization for aerodynamic shape optimization of wind-sensitive structures. 

Aerodynamic shape optimization is very useful for enhancing the performance of wind-sensitive structures. However, shape parameterization, as the first step in the pipeline of aerodynamic shape optimization, still heavily depends on empirical judgment. If not done properly, the resulting small design space may fail to cover many promising shapes, and hence hinder realizing the full potential of aerodynamic shape optimization. To this end, developing a novel shape parameterization scheme that can reflect real-world complexities while being simple enough for the subsequent optimization process is important. This study proposes a machine learning-based scheme that can automatically learn a low-dimensional latent representation of complex aerodynamic shapes for bluff-body wind-sensitive structures. The resulting latent representation (as design variables for aerodynamic shape optimization) is composed of both discrete and continuous variables, which are embedded in a hierarchy structure. In addition to being intuitive and interpretable, the mixed discrete and continuous variables with the hierarchy structure allow stakeholders to narrow the search space selectively based on their interests. As a proof-of-concept study, shape parameterization examples of tall building cross sections are used to demonstrate the promising features of the proposed scheme and guide future investigations on data-driven parameterization for aerodynamic shape optimization of wind-sensitive structures 

At San Francisco State University, a Hispanic Serving Institute and a Primarily Undergraduate Institution, 67% of engineering students are from ethnic minority groups, with only 27% of Hispanic students retained and graduated in their senior year. Additionally, only 14% of students reported full-time employment secured at the time of graduation. Of these secured jobs, only 54% were full-time positions (40+ hours a week). To improve the situation, San Francisco State University, in collaboration with two local community colleges, Skyline and Cañada Colleges, was recently funded by the National Science Foundation through a Hispanic Serving Institute Improving Undergraduate STEM Education Strengthening Student Motivation and Resilience through Research and Advising program to enhance undergraduate engineering education and build capacity for student success. This project will use a data-driven and evidence-based approach to identify the barriers to the success of underrepresented minority students and to generate new knowledge on the best practices for increasing students’ retention and graduation rates, self- efficacy, professional development, and workforce preparedness. Three objectives underpin this overall goal. The first is to develop and implement a Summer Research Internship Program together with community college partners. The second is to establish an HSI Engineering Success Center to provide students with academic resources, networking opportunities with industry, and career development tools. The third is to develop resources for the professional development of faculty members, including Summer Faculty Teaching Workshops, an Inclusive Teaching and Mentoring Seminar Series, and an Engineering Faculty Learning Community. Qualitative and quantitative approaches are used to assess the project outcomes using a survey instrument and interview protocols developed by an external evaluator. This paper discusses an overview of the project and its first-year implementation. The focus is placed on the introduction and implementation of the several main project components, namely the Engineering Success Center, Summer Research Internship Program, and Faculty Summer Teaching Workshop. The preliminary evaluation results, demonstrating the great success of these strategies, are also discussed.