NeuralMPCX is a Python library for building and deploying Model Predictive Controllers with linear, nonlinear, and neural dynamics. The software interfaces CasADi and IPOPT to solve constrained optimal control problems with recurrent neural networks (RNN, LSTM) and state-space systems.
This software was designed with the purpose of anomaly detection and correction for time series water sensor data. This software was developed using the Logan River Observatory data set.
