End-to-End Deep Neural Network Based Nonlinear Model Predictive Control: Experimental Implementation on Diesel Engine Emission Control

David C. Gordon, Armin Norouzi (), Alexander Winkler, Jakub McNally, Eugen Nuss, Dirk Abel, Mahdi Shahbakhti, Jakob Andert and Charles R. Koch
Additional contact information
David C. Gordon: Department of Mechanical Engineering, University of Alberta, 116 St. and 85 Ave, Edmonton, AB T6G 2R3, Canada
Armin Norouzi: Department of Mechanical Engineering, University of Alberta, 116 St. and 85 Ave, Edmonton, AB T6G 2R3, Canada
Alexander Winkler: Teaching and Research Area Mechatronics in Mobile Propulsion, RWTH Aachen University, Forckenbeckstrasse 4, 52074 Aachen, Germany
Jakub McNally: Department of Mechanical Engineering, University of Alberta, 116 St. and 85 Ave, Edmonton, AB T6G 2R3, Canada
Eugen Nuss: Institute of Automatic Control, RWTH Aachen University, Campus-Boulevard 30, 52074 Aachen, Germany
Dirk Abel: Institute of Automatic Control, RWTH Aachen University, Campus-Boulevard 30, 52074 Aachen, Germany
Mahdi Shahbakhti: Department of Mechanical Engineering, University of Alberta, 116 St. and 85 Ave, Edmonton, AB T6G 2R3, Canada
Jakob Andert: Teaching and Research Area Mechatronics in Mobile Propulsion, RWTH Aachen University, Forckenbeckstrasse 4, 52074 Aachen, Germany
Charles R. Koch: Department of Mechanical Engineering, University of Alberta, 116 St. and 85 Ave, Edmonton, AB T6G 2R3, Canada

Energies, 2022, vol. 15, issue 24, 1-23

Abstract: In this paper, a deep neural network (DNN)-based nonlinear model predictive controller (NMPC) is demonstrated using real-time experimental implementation. First, the emissions and performance of a 4.5-liter 4-cylinder Cummins diesel engine are modeled using a DNN model with seven hidden layers and 24,148 learnable parameters created by stacking six Fully Connected layers with one long-short term memory (LSTM) layer. This model is then implemented as the plant model in an NMPC. For real-time implementation of the LSTM-NMPC, an open-source package acados with the quadratic programming solver HPIPM (High-Performance Interior-Point Method) is employed. This helps LSTM-NMPC run in real time with an average turnaround time of 62.3 milliseconds. For real-time controller prototyping, a dSPACE MicroAutoBox II rapid prototyping system is used. A Field-Programmable Gate Array is employed to calculate the in-cylinder pressure-based combustion metrics online in real time. The developed controller was tested for both step and smooth load reference changes, which showed accurate tracking performance while enforcing all input and output constraints. To assess the robustness of the controller to data outside the training region, the engine speed is varied from 1200 rpm to 1800 rpm. The experimental results illustrate accurate tracking and disturbance rejection for the out-of-training data region. At 5 bar indicated mean effective pressure and a speed of 1200 rpm, the comparison between the Cummins production controller and the proposed LSTM-NMPC showed a 7.9% fuel consumption reduction, while also decreasing both nitrogen oxides ( NO x ) and Particle Matter (PM) by up to 18.9% and 40.8%.

Keywords: deep learning; deep neural network; emission reduction; machine learning; long-short-term memory; model predictive control (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/15/24/9335/pdf (application/pdf)
https://www.mdpi.com/1996-1073/15/24/9335/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:15:y:2022:i:24:p:9335-:d:998662

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().