A new project, led by the University of Michigan, could enable industrial competitors to collectively build a predictive model that speeds the development of perovskite solar cells. The aim is to improve upon the process of layer-by-layer deposition of semiconductor materials during production with an information-sharing approach that boosts cooperation between companies while protecting proprietary information and worker interests.
The project is backed by a four-year, $3 million grant from the National Science Foundation and includes partners at the University of California San Diego.
Newer technologies like perovskite semiconductors inevitably pit companies against each other in a race to improve performance, streamline manufacturing and bring products to market. But pure competition slows progress down as companies perform similar experiments, covering the same ground.
The team will seek to incorporate “federated learning” into the process—an approach that allows multiple entities to feed test results into a predictive model that helps all parties improve their manufacturing process while protecting their trade secrets.
“With something like perovskite manufacturing, you have different sources of data on factors such as the optimal processing parameters,” said Raed Al Kontar, U-M assistant professor of industrial and operations engineering.” The question becomes how these different companies that are doing their own research can optimally collaborate and distribute the data they’re collecting through trial and error testing.”
Engineers at U-M, and their partners at UCSD, will conduct isolated experiments with perovskite semiconductors. Al Kontar will take data collected from each to build predictive models for forecasting product quality and performance—helping both to narrow down key parameters such as optimal pressure and temperature during manufacturing.
Pooling information in this way allows for faster progress in development and reduces costs. The NSF considers it a form of “cyber manufacturing,” which “exploits opportunities at the intersection of computing and manufacturing with the potential to radically transform concepts of manufacturing.”
“We’re thinking about how we can use technology to make smaller and medium-sized enterprises competitive in the production of these products,” said Chinedum Okwudire, U-M professor of both mechanical engineering and integrative systems and design.
To do that, the team has Sarah Crane, research manager at U-M’s Economic Growth Institute, and Julie Hui, assistant professor at the School of Information, who studies how technology influences access to work and employment. “Sarah and Julie will help us make sure we understand the landscape out there for those companies—what their needs are in this space, how we can bring them into this ecosystem and how we can help them create jobs.”
