AI optimizes wide-bandgap power converter design
Researchers at Cardiff University and the Compound Semiconductor Applications (CSA) Catapult say they have created a new and more efficient way of modeling and designing wide-bandgap power electronic converters using artificial intelligence (AI). The method, say the researchers, has reduced design times for technology by up to 78% compared to traditional approaches and was used to create a device with an efficiency of over 98%.
Existing design methods largely rely on complex mathematical models, which significantly increases the computational time, complexity and further leads to problems including poor constraint handling capabilities, inaccurate design, difficult parameter tuning and inadequate problem dimension. These all could generate sub-optimal designs that make the whole design process meaningless, say the researchers.
A well-designed power converter must have high efficiency, small volume, be lightweight and have low cost and low failure rate. Therefore, the main goal of a power converter design method is to identify the best trade-off among these performance indicators.
The researchers’ design method used an artificial neural network (ANN)-based multi-objective design approach, which offers significant advantages in reducing the repetitive usage of complex mathematical models and hence the computational time of design. The ANN was trained on an existing dataset of over 2000 designs, so the researchers were able to select the most appropriate design for their desired efficiency and power density.
The researchers selected four major components for the ANN-based design, including power gallium nitrate (GaN) field-effect transistors (FETs), inductors, capacitors, and heat sinks. The design approach was validated through experimental tests on a GaN-based single-phase inverter that was created using the specified design.
The efficiency and power density of the device was well matched to the design and within the range of existing devices, say the researchers, making it technically competitive and commercially viable.
“Accurate and fast transient modelling/simulation approaches are essential to efficiently and to rapidly optimize the performance of wide bandgap power electronics systems,” says co-author of the study Dr Wenlong Ming, Senior Lecturer at Cardiff University and Senior Research Fellow at CSA Catapult. “We are delighted to work together with CSA Catapult to address this gap.”
Co-author of the study Dr Ingo Lüdtke, Head of Power Electronics at CSA Catapult adds, “Automated power electronics design optimization enables the full exploitation of wide bandgap power semiconductor advantages when compared to their silicon counterparts.”
For more, see “Artificial Neural Networks-Based Multi-Objective Design Methodology for Wide-Bandgap Power Electronics Converters.”
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
