Neural Differential Equations for Inverse Modeling in Model Combustors

TL;DR

This paper introduces a neural differential equations-based method for inverse modeling in combustors, enabling accurate inference of unknown boundary conditions from sparse measurements, which enhances fault diagnostics and control.

Contribution

It presents a novel approach combining neural differential equations with physical models to infer unknown quantities from limited data in combustor systems.

Findings

Accurately inferred inlet boundary conditions from sparse temperature data.

Demonstrated robustness to various upstream fluctuation types.

Enabled potential for fault diagnostics and control in power systems.

Abstract

Monitoring the dynamics processes in combustors is crucial for safe and efficient operations. However, in practice, only limited data can be obtained due to limitations in the measurable quantities, visualization window, and temporal resolution. This work proposes an approach based on neural differential equations to approximate the unknown quantities from available sparse measurements. The approach tackles the challenges of nonlinearity and the curse of dimensionality in inverse modeling by representing the dynamic signal using neural network models. In addition, we augment physical models for combustion with neural differential equations to enable learning from sparse measurements. We demonstrated the inverse modeling approach in a model combustor system by simulating the oscillation of an industrial combustor with a perfectly stirred reactor. Given the sparse measurements of the temperature inside the combustor, upstream fluctuations in compositions and/or flow rates can be inferred. Various types of fluctuations in the upstream, as well as the responses in the combustor, were synthesized to train and validate the algorithm. The results demonstrated that the approach can efficiently and accurately infer the dynamics of the unknown inlet boundary conditions, even without assuming the types of fluctuations. Those demonstrations shall open a lot of opportunities in utilizing neural differential equations for fault diagnostics and model-based dynamic control of industrial power systems.