ニューラル状態空間モデル
ニューラル状態空間モデルは、非線形状態空間モデルの一種で、状態遷移関数と測定関数をニューラル ネットワークを使用してモデル化したものです。System Identification Toolbox™ ソフトウェアを使用して、それらのネットワークの重みとバイアスを識別できます。学習させたモデルを制御、推定、最適化、および低次元化モデリングに使用できます。
ライブ エディター タスク
| ニューラル状態空間モデルの推定 | Estimate neural state-space model in the Live Editor (R2023b 以降) |
関数
createMLPNetwork | Create and initialize a Multi-Layer Perceptron (MLP) network to be used within a neural state-space system (R2022b 以降) |
setNetwork | Assign dlnetwork object as the state or output function of a
neural state-space model (R2024b 以降) |
nssTrainingOptions | Create training options object for neural state-space systems (R2022b 以降) |
nlssest | Estimate nonlinear state-space model using measured time-domain system data (R2022b 以降) |
generateMATLABFunction | Generate MATLAB functions that evaluate the state and output functions, and their Jacobians, of a nonlinear grey-box or neural state-space model (R2022b 以降) |
idNeuralStateSpace/evaluate | Evaluate a neural state-space system for a given set of state and input values and return state derivative (or next state) and output values (R2022b 以降) |
idNeuralStateSpace/linearize | Linearize a neural state-space model around an operating point (R2022b 以降) |
sim | 同定されたモデルの応答のシミュレーション |
オブジェクト
idNeuralStateSpace | Neural state-space model with identifiable network weights (R2022b 以降) |
nssTrainingADAM | Adam training options object for neural state-space systems (R2022b 以降) |
nssTrainingSGDM | SGDM training options object for neural state-space systems (R2022b 以降) |
nssTrainingRMSProp | RMSProp training options object for neural state-space systems (R2024b 以降) |
nssTrainingLBFGS | L-BFGS training options object for neural state-space systems (R2024b 以降) |
ブロック
| Neural State-Space Model | Simulate neural state-space model in Simulink (R2022b 以降) |
トピック
- What Are Neural State-Space Models?
Understand the structure of a neural state-space model.
- Neural State-Space Model of SI Engine Torque Dynamics
This example describes reduced order modeling (ROM) of the nonlinear torque dynamics of a spark-ignition (SI) engine using a neural state-space model. The identified model can be used for hardware-in-the-loop (HIL) testing, powertrain control, diagnostics, and training algorithm design. For example, you can use the model for after-treatment control and diagnostic algorithm development. For more information on neural state-space models, see Neural State-Space Models.
- Neural State-Space Model of Simple Pendulum System
This example shows how to design and train a deep neural network that approximates a nonlinear state-space system in continuous time.
- Augment Known Linear Model with Flexible Nonlinear Functions
This example demonstrates a method to improve the normalized root mean-squared error (NRMSE) fit score of an existing state-space model using a neural state-space model.
- Reduced Order Modeling of a Nonlinear Dynamical System Using Neural State-Space Model with Autoencoder
This example shows reduced order modeling of a nonlinear dynamical system using a neural state-space (NSS) modeling technique. The nonlinear system used to describe the approach is a cascade of nonlinear mass-spring-damper (MSD) systems. The development of the reduced order model hinges on training a neural network with three parts:
- Reduced Order Modeling of Electric Vehicle Battery System Using Neural State-Space Model
This example shows 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.
