Software Open Access
NeuralMPCX: A Model Predictive Control library that supports classic MPC and neural MPC with CasADi
Lopes Junior, Enio;
Reinecke, Sebastian
NeuralMPCX is a Python library for building and deploying Model Predictive Controllers with classic and neural dynamical models. You write constrained MPC with RNN/LSTM models in a CasADi/IPOPT workflow. The library handles CasADi RNN integration, warm-starting, constraint management, real-time feasibility, and both LTI state-space and neural dynamics in one framework. You can run neural and classical MPC controllers side by side.
Files
(259.1 kB)
| Name | Size | |
|---|---|---|
|
hzdr/neural-mpcx-v2.1.0.zip
md5:3ae99a3c1cf2c8ce021be97ff99888da |
259.1 kB | Download |
1,560
43
views
downloads
| All versions | This version | |
|---|---|---|
| Views | 1,560 | 210 |
| Downloads | 43 | 8 |
| Data volume | 18.6 MB | 2.1 MB |
| Unique views | 1,445 | 204 |
| Unique downloads | 37 | 8 |
Available in
- Publication date:
- June 11, 2026
- DOI:
-
- Keyword(s):
- Neural Model Predictive Control Recurrent Neural Networks Long Short-Term Memory RNN LSTM MPC Nonlinear Model Predictive Control Linear Model Predictive Control
- Related identifiers:
- Identical to:
https://www.hzdr.de/publications/Publ-43156 - Supplement to:
https://github.com/hzdr/neural-mpcx/tree/v2.1.0 - Communities:
- License (for files):
- Apache License 2.0