Introducing a Deep Neural Network-Based Model Predictive Control Framework for Rapid Controller Implementation

Proceedings of the ... American Control Conference/Proceedings of the American Control Conference, pp. 5232–5237

Abstract

Model Predictive Control (MPC) provides an optimal control solution based on a cost function while allowing for the implementation of process constraints. As a model-based optimal control technique, the performance of MPC strongly depends on the model used where a tradeoff between model computation time and prediction performance exists. One solution is the integration of MPC with a machine learning (ML) based process model which are quick to evaluate online. This work presents the experimental implementation of a deep neural network (DNN) based nonlinear MPC for Homogeneous Charge Compression Ignition (HCCI) combustion control. The DNN model consists of a Long Short-Term Memory (LSTM) network surrounded by fully connected layers which was trained using experimental engine data and showed acceptable prediction performance with under 5% error for all outputs. Using this model, the MPC is designed to track the Indicated Mean Effective Pressure (IMEP) and combustion phasing trajectories, while minimizing several parameters. Using the acados software package to enable the real-time implementation of the MPC on an ARM Cortex A72, the optimization calculations are completed within 1.4 ms. The external A72 processor is integrated with the prototyping engine controller using a UDP connection allowing for rapid experimental deployment of the NMPC. The IMEP trajectory following of the developed controller was excellent, with a root-mean-square error of 0.133 bar, in addition to observing process constraints.

Authors 6

1. Alexander Winkler Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Teaching and Research Area Mechatronics in Mobile Propulsion,Aachen,Germany,52074

2. Julian Bedei Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Teaching and Research Area Mechatronics in Mobile Propulsion,Aachen,Germany,52074

3. Patrick Schaber Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Teaching and Research Area Mechatronics in Mobile Propulsion,Aachen,Germany,52074

4. Stefan Pischinger Aachen Chair of Thermodynamics of Mobile Energy Conversion Systems (TME)

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Chair of Thermodynamics of Mobile Energy Conversion Systems,Aachen,Germany,52074

5. Jakob Andert Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Teaching and Research Area Mechatronics in Mobile Propulsion,Aachen,Germany,52074

6. Charles Robert Koch

   University of Alberta

   Affiliation as printed

   University of Alberta,Edmonton,AB,Canada,T6G 2R3