Identifying parameters for building high-density, additively-manufactured parts.  It is a challenge to determine process parameters to use in building high-density metal parts with laser powder-bed fusion, especially for materials that have never been additively manufactured before. We show how simple simulations and experiments, combined with data analysis, can help guide the selection of optimal parameters.

Data mining techniques for use in additive manufacturing. Laser powder bed fusion is a rich source of problems that can be addressed using data analysis techniques. These include i) feature selection and parallel plots to identify important process parameters; ii) sampling and surrogates for exploring the input design space and for solving inverse problems; iii) self-organizing maps to understand the solution to the inverse problem; and iv) Gaussian process regression for prediction with associated uncertainties. By incorporating these techniques into an efficient iterative approach that starts with simple experiments and simulations to understand the design space, and moves to progressively more complex experiments and simulations as we get closer to a solution, we can reduce the time it takes to address problems of interest.

WindSENSE:Integrating wind energy on the power grid is a challenge, especially with increasing installed wind capacity, the presence of ramp events where the energy increases or decreases by a large amount in a short time, and the need to keep the grid balanced. Taking a data-oriented approach to the problem, we focused on two topics: i) how do we best make use of existing data; and ii) what new data should we collect to improve short-term and extreme-event weather forecasts. This was joint work with AWS TruePower, in collaboration with Bonneville Power Administration (BPA), California Independent System Operator (CaISO), and Southern California Edison (SCE).