A non-intrusive approach to index-aware learning
This work provides an incremental improvement to a method for learning physics-consistent solutions to DAEs, which is important for engineers and researchers working with electrical circuit simulations.
This paper introduces a non-intrusive variant of the index-aware learning framework, which is designed to learn time and parameter-dependent solutions for differential-algebraic equations (DAEs), specifically those found in electrical circuits. The method ensures physics-consistent solutions by maintaining inherent constraints, such as Kirchhoff's laws, and is demonstrated using a buck converter example.
We present a non-intrusive version of the index-aware learning framework introduced in arXiv:2309.00958. Index-aware learning itself is an approach for learning the time and parameter dependent solutions of differential-algebraic equations (DAEs), in particular those of electrical circuits. A key feature of the approach is that it ensures the learned solutions to remain physics-consistent, i.e.\ inherent constraints of the solution, such as e.g.\ Kirchhoff's laws, remain fulfilled. In general, this is achieved by leveraging a decoupling of the DAE into its differential and algebraic parts, while the non-intrusive version of the approach additionally relies on results from arXiv:2604.20475 and arXiv:2107.07755. We illustrate the overall workflow and compare the non-intrusive and intrusive versions using a buck converter as an example.