Publications

 

Journal Papers

  • M.Mejari, B.Mavkov, M.Forgione, and D.Piga. Direct identification of continuous-time LPV state-space models via an integral architecture. To appear in Automatica, 2022.
  • D.Piga, M.Mejari, and M.Forgione. Learning dynamical systems from quantized observations: a Bayesian perspective. To appear in IEEE Transactions on Automatic Control, 2022.
  • M.Forgione and D. Piga. Continuous-time system identification with neural networks: model structures and fitting criteria. European Journal of Control, volume 59, pp 69-81, 2021. Arxiv preprint. Github code repository.
  • M.Forgione and D. Piga. dynoNet: a neural network architecture for learning dynamical systems. International Journal of Adaptive Control and Signal Processing, 2021. Arxiv preprint. Github code repository.
  • L. Roveda, M. Forgione, D. Piga. Robot control parameters auto-tuning in trajectory tracking applications. Control Engineering Practice, 101(2020), pp 72-78, 2020.
  • B. Mavkov, M. Forgione, D. Piga. Integrated Neural Networks for Nonlinear Continuous-Time System Identification. IEEE Control Systems Letters, 4(4), pp 851-856, 2020.
  • D. Piga, M. Forgione, S. Formentin, A. Bemporad. Performance-oriented model learning for data-driven MPC design. IEEE Control Systems Letters, 3(3), pp 577-582, 2019. Paper. Bibtex file. Matlab code. Presentation.
  • M. Forgione, X. Bombois, P.M.J. Van den Hof. Data-driven model improvement for model-based control. Automatica, 52(2015), pp. 118-124, 2015. Paper (preprint). Bibtex file.
  • M. Forgione , G. Birpoutsoukis, X Bombois, P.J. Daudey and P.M.J. Van den Hof. Batch-to-batch model improvement for cooling crystallization. Control Engineering Practice, 41(2015), pp 72-78, 2015. Paper (preprint).
  • A.Mesbah, X.Bombois, J.H.A.Ludlage, H.Hjalmarsson, M.Forgione, P.M.J. Van den Hof. Least Costly Closed-loop Performance Diagnosis and Plant Re-identification. International Journal of Control, 88(11), pp 2264-2276, 2015.
  • S.Kadam, J.Vissers, M.Forgione, R.Geertman, P.Daudey, P.J.Stankiewicz, H.Kramer. Rapid Crystallization Process Development Strategy from Lab to Industrial Scale with PAT tools in skid configuration, in press, Org. Process Res & Dev. 16(5), pp. 769-780. Bibtex file.
  • L.Magni, M.Forgione, C.Toffanin, C.Dalla Man, B.Kovatchev, G.De Nicolao, C.Cobelli. Artificial Pancreas Systems: Run-to-Run Tuning of Model Predictive Control for Type 1 Diabetes Subjects: In Silico Trial. Journal of diabetes science and technology (Online), vol. 4, no. 5, pp. 1091, 2009. Bibtex file.

Refereed Conference Proceedings

  • L.H. Peeters, G.I. Beintema, M. Forgione, and M. Schoukens. NARX Identification using Derivative-Based Regularized Neural Networks. In Proceedings of the 61st IEEE Conference on Decision and Control, 2022. Paper.
  • X. Bombois and M. Forgione. Control Design via Bayesian Optimization with Safety Constraints. In Proceedings of the 6th IEEE Conference on Control Technology and Applications, 2022. Paper.
  • M. Mejari, B. Mavkov, M. Forgione, and D. Piga. An Integral Architecture for Identification of Continuous-Time State-Space LPV Models. In Proceedings of the 4th IFAC Workshop on Linear Parameter-Varying Systems. Paper.
  • D. Piga, M.Forgione and M. Mejari. Deep learning with transfer functions: new applications in system identification. In Proceedings of the 2021 SysId Conference, 2021. Arxiv preprint. Github code repository.
  • M. Mejari, M.Forgione, and D. Piga. An integral architecture for identification of continuous-time state-space LPV models. In Proceedings of the 4th IFAC Workshop on Linear Parameter Varying Systems (LPV), 2021.
  • M.Forgione and D. Piga. Model structures and fitting criteria for system identification with neural networks. In Proceedings of the 14th IEEE International Conference Application of Information and Communication Technologies, 2020. Arxiv preprint. Github code repository.
  • M. Forgione, D. Piga, and A. Bemporad. Efficient Calibration of Embedded MPC. In Proceedings of the 21st IFAC World Congress, 2020. Arxiv preprint. Github code repository.
  • L. Roveda, M. Forgione, D. Piga. Two-Stage Robot Controller Auto-Tuning Methodology for Trajectory Tracking Applications. In Proceedings of the 21st IFAC World Congress, 2020.
  • L. Roveda, M. Forgione, and D. Piga. Control Parameters Tuning Based on Bayesian Optimization for Robot Trajectory Tracking. ICRA19 Workshop on Learning for Industry 4.0: Feasibility and Challenges.
  • A.C.P.M. Backx, X.J.A. Bombois, P.J. Daudey, M. Forgione, R.M. Geertman, P.M.J. Van den Hof, S.S. Kadam, H.J.A. Kramer, J.A.W. Vissers, P. Vonk, G.M. Westhoff. Towards a more rigorous control of seeded batch crystallization. In Proceedings of the 19th International Simposium on Industrial Crystallization. Tolouse, France, Speptember 2014. Bibtex file.
  • M.Forgione, X.Bombois, P.M.J.Van den Hof and H.Hjalmarsson. Experiment design for parameter estimation in nonlinear systems based on multilevel excitation. In Proceedings of the 2014 European Control Conference, pages 25-30, Strasbourg Convention and Exhibition Center, Strasbourg, France, June 2014. Paper . Matlab code. Bibtex file.
  • M.G. Potters, X.Bombois, M. Forgione, P.E.Modén, M.Lundh, H.Hjalmarsson and P.M.J.Van den Hof. Optimal Experiment Design in Closed Loop with Unknown, Nonlinear or Implicit Controllers using Stealth Identification. In Proceedings of the 2014 European Control Conference, pages 726-731, Strasbourg Convention and Exhibition Center, Strasbourg, France, June 2014. Bibtex file.
  • M.Forgione, X.Bombois and P.M.J.Van den Hof. Experiment design for batch-to-batch model-based learning control. In Proceedings of the 2013 American Control Conference, pages 3918-3923, Washington, DC, USA, June 17-19, 2013. Paper. Slides. Bibtex file.
  • M.Forgione, A.Mesbah, X.Bombois, P.M.J.Van den Hof. Iterative Learning Control of Supersaturation in Batch Cooling Crystallization. In Proceedings of the 2012 American Control Conference, pages 6455–6460, Fairmont Queen Elizabeth, Montreal, Canada, 2012. Paper. Slides. Bibtex file.
  • M.Forgione, A.Mesbah, X.Bombois, and P.M.J.Van den Hof. Batch-to-batch strategies for cooling crystallization. In Proceedings of the 51st IEEE Conference on Decision and Control, pages 6364-6369, Maui, Hawaii. Paper. Slides. Bibtex file.
  • A.Mesbah, X.Bombois, M.Forgione, J.H.A.Ludlage, P.E.Modén, H. Hjalmarsson and P.M.J. Van den Hof. A Unified Experiment Design Framework for Detection and Identification in Closed-loop Performance Diagnosis. In Proceedings of the 51st IEEE Conference on Decision and Control, pages 2152-2157, Maui, Hawaii. Bibtex file.
  • S.Kadam, J.Vissers, M.Forgione, R.Geertman, P.Daudey, H.Kramer. Rapid Determination of a near-optimal seeding procedure at an industrial scale batch crystallizer. In Proceedings of the 18th International Simposium on Industrial Crystallization, pages 141-142, 2012, Zurich, 2012. Bibtex file.
  • J.Vissers, M.Forgione, S.Kadam, P.Daudey, T.Backx, A.Huesman, H.Kramer, P.M.J.Van Den Hof. Novel control of supersaturation on an industrial scale pharmaceutical batch crystallizerIn. In Proceedings of the 18th International Simposium on Industrial Crystallization, pages 141-142, 2012, Zurich, 2012. Bibtex file.

Patents

  • S.Baldo, A. Gallivanoni, M. Forgione, and C. Pastore. Control circuits and methods for distributed induction heating devices, 2019. Link to the EPO web site. PDF file.

Theses

  • M.Forgione. Batch-to-batch learning for model-based control of process systems with application to cooling crystallization Ph.D. Thesis, Delft University of Technology, 2014. PDF file.
  • M.Forgione. Pancreas Artificiale: identificazione di modelli a scatola nera del metabolismo glucosio-insulina. (Artificial Pancreas: identification of black-box models of the glucose-insuline metabolism.) Master's Thesis, University of Pavia, 2009. Zipped PDF file.
  • M.Forgione. Progettazione, Modellizzazione e Controllo di un Carroponte. (Design, modeling and control of a gantry crane.) Bachelor's Thesis, University of Pavia, 2007. Zipped PDF File.

Non-refereed Conference Proceedings

  • M.Forgione and D. Piga. dynoNet: a neural network architecture for learning dynamical systems. SIDRA Conference, 2020. Arxiv preprint. Github code repository.
  • M.Forgione, X.Bombois and P.M.J.Van den Hof. Experiment design for batch-to-batch model-based learning control, in 32th Benelux Meeting on Systems and Control. Houffalize, Belgium, 26-28 March 2013. Slides.
  • M.Forgione, A.Mesbah, X.Bombois, P.M.J.Van den Hof. Batch-to-batch control of supersaturation in cooling crystallization with a measurement-based model update, in 30th Benelux Meeting on Systems and Control. Lommel, Belgium, 15-17 March 2012. Slides.
  • M.Forgione. Time domain design of experiments for linear and nonlinear systems, in 29th Benelux Meeting on Systems and Control. Heijderbos, Heijen/Nijmegen, The Netherlands, 27-29 March 2011. Slides.

Orals

  • M.Forgione. Iterative model improvement for model-based control. Presented at 2013 Europen Research Network on System Identification (ERNSI), Pont-à-Mousson, France, September 22-25 2013. Slides.