Analysis of Numerical Integration in RNN-Based Residuals for Fault Diagnosis of Dynamic Systems
This work addresses the problem of enhancing fault diagnosis accuracy for dynamic systems like industrial machinery, but it is incremental as it focuses on solver selection within an existing neural ODE framework.
The paper investigates how the choice of numerical solver affects the performance of neural ordinary differential equation (neural ODE) residuals in fault diagnosis for dynamic systems, using a case study of a heavy-duty truck's after-treatment system to demonstrate potential improvements.
Data-driven modeling and machine learning are widely used to model the behavior of dynamic systems. One application is the residual evaluation of technical systems where model predictions are compared with measurement data to create residuals for fault diagnosis applications. While recurrent neural network models have been shown capable of modeling complex non-linear dynamic systems, they are limited to fixed steps discrete-time simulation. Modeling using neural ordinary differential equations, however, make it possible to evaluate the state variables at specific times, compute gradients when training the model and use standard numerical solvers to explicitly model the underlying dynamic of the time-series data. Here, the effect of solver selection on the performance of neural ordinary differential equation residuals during training and evaluation is investigated. The paper includes a case study of a heavy-duty truck's after-treatment system to highlight the potential of these techniques for improving fault diagnosis performance.