Reduced Order Modeling

Extend deep learning workflows in areas of reduced order modeling (ROM)

Use Deep Learning Toolbox™ for reduced order modeling (ROM) tasks.

Reduced order modeling (ROM) is a technique that can simplify complex and high-fidelity models and simulations by reducing the computational complexity while preserving the model behavior and accuracy. For example, you can replace computationally intensive subsystems in a Simulink model with a trained neural network that makes realistic predictions.

Functions

exportNetworkToSimulinkGenerate Simulink model that contains deep learning layer blocks and subsystems that correspond to deep learning layer objects (Since R2024b)

Blocks

PredictPredict responses using a trained deep learning neural network (Since R2020b)
Stateful PredictPredict responses using a trained recurrent neural network (Since R2021a)

Topics

Related Information

Featured Examples

Reduced Order Modeling of Electric Vehicle Battery System Using Neural State-Space Model

Reduced Order Modeling of Electric Vehicle Battery System Using Neural State-Space Model

A reduced order modeling (ROM) workflow, where you use deep learning to obtain a low-order nonlinear state-space model that serves as a surrogate for a high-fidelity battery model. The low-order model takes the current (charge or discharge) and state of charge (SOC) as inputs and predicts voltage and temperature of an electric vehicle (EV) battery module while the battery is being cooled by an edge-cooled plate with a coolant at a constant flow rate. You train the low-order model and deploy it in Simulink® to compare it against the high-fidelity model.

(System Identification Toolbox)