The more complex modern electronic systems have gotten – the less comprehensive simulation has become as a design tool. But there's a solution on the horizon in the form of behavioral modeling based on machine learning. One of the leading centers behind this research is the Center for Advanced Electronics through Machine Learning (CAEML) at the University of Illinois at Urbana-Champaign. Funded by the National Science Foundation and formed with the aim of applying machine-learning techniques to microelectronics and micro-systems modeling, CAEML is already conducting research into several areas including: Design Optimization of High-Speed Links; Nonlinear Modeling of Power Delivery Networks; and Modeling for Design Reuse.
“The limitations in simulation that people experience have always been there. But people are trying to do more ambitious things. And we need more accurate models than we've had in the past,” Elyse Rosenbaum , director of CAEML told Design News in an interview. “For example, we make everything smaller. The physical accuracy of the models hasn't changed, but we're entering regimes where there's increasing cross talks between components simply because we're packing them together more closely.”
Rosenbaum, who will be delivering a keynote on machine learning and electronics modeling at DesignCon 2017 , said new product demands, such as the push for greener technologies – which calls for ever-improving energy minimization – are creating an environment for design engineers in which simulation-based verification alone is simply not practical. “When you're designing a product, such as, say, a cellphone, you have maybe about a hundred or so components on the circuit board. That's a lot of design values. To completely explore that design space and try every possible combination of components is unfeasible. You'd never get your product out of the door,” Rosenbaum said.
The solution then for Rosenbaum and the researchers at CAEML is highly abstracted behavioral models that let engineers rapidly do a design space exploration to find an optimal sign, not just one that's good enough.
“When we want to do design optimization we can't be concerned with every single variable inside the system,” Rosenbaum said. “All we really care about is what's happening in the aggregate – the signals at the outside of the device where the humans are interacting with it. So we want these abstracted models and that's what machine learning gives you – models that you then use for simulation.”
Accomplishing this is no small task, given that simulations require engineers to model everything in a system, and all of those effects can be represented. What Rosenbaum and her team are seeking is completely data-driven modeling, not based on any prior knowledge of what's inside the system. To do this they need to use machine learning algorithms to that can predict a particular output and represent the behaviors of particular components.