% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Vaupel:888993,
      author       = {Vaupel, Yannic and Hamacher, Nils C. and Caspari, Adrian
                      and Mhamdi, Adel and Kevrekidis, Ioannis G. and Mitsos,
                      Alexander},
      title        = {{A}ccelerating nonlinear model predictive control through
                      machine learning},
      journal      = {Journal of process control},
      volume       = {92},
      issn         = {0959-1524},
      address      = {Amsterdam [u.a.]},
      publisher    = {Elsevier Science},
      reportid     = {FZJ-2020-05380},
      pages        = {261 - 270},
      year         = {2020},
      abstract     = {The high computational requirements of nonlinear model
                      predictive control (NMPC) are a long-standing issue and,
                      among other methods, learning the control policy with
                      machine learning (ML) methods has been proposed in order to
                      improve computational tractability. However, these methods
                      typically do not explicitly consider constraint
                      satisfaction. We propose two methods based on learning the
                      optimal control policy by an artificial neural network (ANN)
                      and using this for initialization to accelerate computations
                      while meeting constraints and achieving good objective
                      function value. In the first, the ANN prediction serves as
                      the initial guess for the solution of the optimal control
                      problem (OCP) solved in NMPC. In the second, the ANN
                      prediction is improved by solving a single quadratic program
                      (QP). We compare the performance of the two proposed
                      strategies against two benchmarks representing the extreme
                      cases of (i) solving the NMPC problem to convergence using
                      the shift-initialization strategy and (ii) implementing the
                      controls predicted by the ANN prediction without further
                      correction to reduce the computational delay. We find that
                      the proposed ANN initialization strategy mostly results in
                      the same control policy as the shift-initialization
                      strategy. The computational times are on average $45\%$
                      longer but the maximum time $is42\%$ smaller and the
                      distribution is tighter, thus more predictable. The proposed
                      QP-based method yields a good compromise between finding the
                      optimal control policy and solution time. Closed-loop
                      infeasibilities are negligible and the objective function is
                      typically greatly improved as compared to benchmark (ii).
                      The computational time required for the necessary
                      second-order sensitivity integration is typically an order
                      of magnitude smaller than for solving the NMPC problem to
                      convergence. Previous article in issue},
      cin          = {IEK-10},
      ddc          = {004},
      cid          = {I:(DE-Juel1)IEK-10-20170217},
      pnm          = {899 - ohne Topic (POF3-899)},
      pid          = {G:(DE-HGF)POF3-899},
      typ          = {PUB:(DE-HGF)16},
      UT           = {WOS:000567786500021},
      doi          = {10.1016/j.jprocont.2020.06.012},
      url          = {https://juser.fz-juelich.de/record/888993},
}