More Like this

1. An Online Transfer Learning Approach for Identification and Predictive Control Design with Application to RCCI Engines

   Bao, Yajie; Mohammadpour Velni, Javad; Shahbakhti, Mahdi (January 2020, 2020 ASME Dynamic Systems Control Conference)

   null (Ed.)

   This paper presents a framework to refine identified artificial neural networks (ANN) based state-space linear parametervarying (LPV-SS) models with closed-loop data using online transfer learning. An LPV-SS model is assumed to be first identified offline using inputs/outputs data and a model predictive controller (MPC) designed based on this model. Using collected closed-loop batch data, the model is further refined using online transfer learning and thus the control performance is improved. Specifically, fine-tuning, a transfer learning technique, is employed to improve the model. Furthermore, the scenario where the offline identified model and the online controlled system are “similar but not identitical” is discussed. The proposed method is verified by testing on an experimentally validated high-fidelity reactivity controlled compression ignition (RCCI) engine model. The verification results show that the new online transfer learning technique combined with an adaptive MPC law improves the engine control performance to track requested engine loads and desired combustion phasing with minimum errors. 

   more » « less
2. Data-Driven Modeling and Predictive Control of Combustion Phasing for RCCI Engines

   Khoshbakht Irdmousa, Behrouz; Rizvi, Syed Z; Mohammadpour Velni, Javad; Naber, Jeffrey; Shahbakhti, Mahdi (July 2019, Proceedings of the ... American Control Conference)

   Reactivity controlled compression ignition (RCCI) engines center on a combustion strategy with higher thermal efficiency, lower particulate matter (PM), and lower oxides of nitrogen (NOx) emissions compared to conventional diesel combustion (CDC) engines. However, real time optimal control of RCCI engines is challenging during transient operation due to the need for high fidelity combustion models. Development of a simple, yet accurate control-oriented RCCI model from physical laws is time consuming and often requires substantial calibrations. To overcome these challenges, data-driven models can be developed. In this paper, a data-driven linear parameter varying (LPV) model for an RCCI engine is developed. An LPV state space model is identified to predict RCCI combustion phasing as a function of multiple RCCI control variables. The results show that the proposed method provides a fast and reliable route to identify an RCCI engine model. The developed model is then used for the design of a model predictive controller (MPC) to control crank angle for 50% fuel burnt (CA50) for varying engine conditions. The experimental results show that the designed MPC with the data-driven LPV model can track desired CA50 with less than 1 crank angle degree (CAD) error against changes in engine load. 

   more » « less
3. Data-driven Modeling and Predictive Control of Combustion Phasing for RCCI Engines

   Khoshbakht Irdmousa, Behrouz; Rizvi, Syed Z; Mohammadpour Velni, Javad; Naber, Jeffrey; Shahbakhti, Mahdi (January 2019, Proceedings of the ... American Control Conference)

   Reactivity controlled compression ignition (RCCI) engines center on a combustion strategy with higher thermal efficiency, lower particulate matter (PM), and lower oxides of nitrogen (NOx) emissions compared to conventional diesel combustion (CDC) engines. However, real time optimal control of RCCI engines is challenging during transient operation due to the need for high fidelity combustion models. Development of a simple, yet accurate control-oriented RCCI model from physical laws is time consuming and often requires substantial calibrations. To overcome these challenges, data-driven models can be developed. In this paper, a data-driven linear parametervarying (LPV) model for an RCCI engine is developed. An LPV state space model is identified to predict RCCI combustion phasing as a function of multiple RCCI control variables. The results show that the proposed method provides a fast and reliable route to identify an RCCI engine model. The developed model is then used for the design of a model predictive controller (MPC) to control crank angle for 50% fuel burnt (CA50) for varying engine conditions. The experimental results show that the designed MPC with the data-driven LPV model can track desired CA50 with less than 1 crank angle degree (CAD) error against changes in engine load. 

   more » « less
4. Data-Driven Modeling and Predictive Control of Combustion Phasing for RCCI Engines

   Khoshbakht Irdmousa, Behrouz; Rizvi, Syed Z; Mohammadpour Velni, Javad; Naber, Jeffrey; Shahbakhti, Mahdi (July 2019, Proceedings of the American Control Conference)

   Reactivity controlled compression ignition (RCCI) engines center on a combustion strategy with higher thermal efficiency, lower particulate matter (PM), and lower oxides of nitrogen (NOx) emissions compared to conventional diesel combustion (CDC) engines. However, real time optimal control of RCCI engines is challenging during transient operation due to the need for high fidelity combustion models. Development of a simple, yet accurate control-oriented RCCI model from physical laws is time consuming and often requires substantial calibrations. To overcome these challenges, data-driven models can be developed. In this paper, a data-driven linear parametervarying (LPV) model for an RCCI engine is developed. An LPV state space model is identified to predict RCCI combustion phasing as a function of multiple RCCI control variables. The results show that the proposed method provides a fast and reliable route to identify an RCCI engine model. The developed model is then used for the design of a model predictive controller (MPC) to control crank angle for 50% fuel burnt (CA50) for varying engine conditions. The experimental results show that the designed MPC with the data-driven LPV model can track desired CA50 with less than 1 crank angle degree (CAD) error against changes in engine load. 

   more » « less
5. Learning‐based adaptive‐scenario‐tree model predictive control with improved probabilistic safety using robust Bayesian neural networks

   https://doi.org/10.1002/rnc.6560  

   Bao, Yajie; Chan, Kimberly J.; Mesbah, Ali; Velni, Javad Mohammadpour (December 2022, International Journal of Robust and Nonlinear Control)

   Summary Scenario‐based model predictive control (MPC) methods can mitigate the conservativeness inherent to open‐loop robust MPC. Yet, the scenarios are often generated offline based on worst‐case uncertainty descriptions obtaineda priori, which can in turn limit the improvements in the robust control performance. To this end, this paper presents a learning‐based, adaptive‐scenario‐tree model predictive control approach for uncertain nonlinear systems with time‐varying and/or hard‐to‐model dynamics. Bayesian neural networks (BNNs) are used to learn a state‐ and input‐dependent description of model uncertainty, namely the mismatch between a nominal (physics‐based or data‐driven) model of a system and its actual dynamics. We first present a new approach for training robust BNNs (RBNNs) using probabilistic Lipschitz bounds to provide a less conservative uncertainty quantification. Then, we present an approach to evaluate the credible intervals of RBNN predictions and determine the number of samples required for estimating the credible intervals given a credible level. The performance of RBNNs is evaluated with respect to that of standard BNNs and Gaussian process (GP) as a basis of comparison. The RBNN description of plant‐model mismatch with verified accurate credible intervals is employed to generate adaptive scenarios online for scenario‐based MPC (sMPC). The proposed sMPC approach with adaptive scenario tree can improve the robust control performance with respect to sMPC with a fixed, worst‐case scenario tree and with respect to an adaptive‐scenario‐based MPC (asMPC) using GP regression on a cold atmospheric plasma system. Furthermore, closed‐loop simulation results illustrate that robust model uncertainty learning via RBNNs can enhance the probability of constraint satisfaction of asMPC. 

   more » « less