{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T09:54:24Z","timestamp":1780048464924,"version":"3.53.1"},"reference-count":41,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2021,6,26]],"date-time":"2021-06-26T00:00:00Z","timestamp":1624665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>The attainment of a satisfactory operating point is one of the main problems in the tuning of particle accelerators. These are extremely complex facilities, characterized by the absence of a model that accurately describes their dynamics, and by an often persistent noise which, along with machine drifts, affects their behaviour in unpredictable ways. In this paper, we propose an online iterative Linear Quadratic Regulator (iLQR) approach to tackle this problem on the FERMI free-electron laser of Elettra Sincrotrone Trieste. It consists of a model identification performed by a neural network trained on data collected from the real facility, followed by the application of the iLQR in a Model-Predictive Control fashion. We perform several experiments, training the neural network with increasing amount of data, in order to understand what level of model accuracy is needed to accomplish the task. We empirically show that the online iLQR results, on average, in fewer steps than a simple gradient ascent (GA), and requires a less accurate neural network to achieve the goal.<\/jats:p>","DOI":"10.3390\/info12070262","type":"journal-article","created":{"date-parts":[[2021,6,27]],"date-time":"2021-06-27T22:24:57Z","timestamp":1624832697000},"page":"262","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["An Online Iterative Linear Quadratic Approach for a Satisfactory Working Point Attainment at FERMI"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0059-1176","authenticated-orcid":false,"given":"Niky","family":"Bruchon","sequence":"first","affiliation":[{"name":"Department of Engineering and Architecture, University of Trieste, 34127 Trieste, TS, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0867-8388","authenticated-orcid":false,"given":"Gianfranco","family":"Fenu","sequence":"additional","affiliation":[{"name":"Department of Engineering and Architecture, University of Trieste, 34127 Trieste, TS, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9000-9874","authenticated-orcid":false,"given":"Giulio","family":"Gaio","sequence":"additional","affiliation":[{"name":"IT Group, Elettra Sincrotrone Trieste, 34149 Basovizza, TS, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2634-3437","authenticated-orcid":false,"given":"Simon","family":"Hirlander","sequence":"additional","affiliation":[{"name":"IDA Lab Salzburg, University of Salzburg, 5020 Salzburg, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9738-2353","authenticated-orcid":false,"given":"Marco","family":"Lonza","sequence":"additional","affiliation":[{"name":"IT Group, Elettra Sincrotrone Trieste, 34149 Basovizza, TS, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4423-1666","authenticated-orcid":false,"given":"Felice Andrea","family":"Pellegrino","sequence":"additional","affiliation":[{"name":"Department of Engineering and Architecture, University of Trieste, 34127 Trieste, TS, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3815-6652","authenticated-orcid":false,"given":"Erica","family":"Salvato","sequence":"additional","affiliation":[{"name":"Department of Engineering and Architecture, University of Trieste, 34127 Trieste, TS, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/0375-9601(76)90561-2","article-title":"Theory of a free electron laser","volume":"59","author":"Colson","year":"1976","journal-title":"Phys. Lett. A"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1016\/0168-9002(86)90916-2","article-title":"An analysis of self-amplified spontaneous emission","volume":"250","author":"Kim","year":"1986","journal-title":"Nucl. Instrum. Methods Phys. Res. Sect. A Accel. Spectrom. Detect. Assoc. Equip."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"5178","DOI":"10.1103\/PhysRevA.44.5178","article-title":"Generation of intense UV radiation by subharmonically seeded single-pass free-electron lasers","volume":"44","author":"Yu","year":"1991","journal-title":"Phys. Rev. A"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1038\/nphoton.2012.233","article-title":"Highly coherent and stable pulses from the FERMI seeded free-electron laser in the extreme ultraviolet","volume":"6","author":"Allaria","year":"2012","journal-title":"Nat. Photonics"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"913","DOI":"10.1038\/nphoton.2013.277","article-title":"Two-stage seeded soft-X-ray free-electron laser","volume":"7","author":"Allaria","year":"2013","journal-title":"Nat. Photonics"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1107\/S1600577515005366","article-title":"The FERMI free-electron lasers","volume":"22","author":"Allaria","year":"2015","journal-title":"J. Synchrotron Radiat."},{"key":"ref_7","unstructured":"Tomin, S., Geloni, G., Zagorodnov, I., Egger, A., Colocho, W., Valentinov, A., Fomin, Y., Agapov, I., Cope, T., and Ratner, D. (2016, January 8\u201313). Progress in Automatic Software-based Optimization of Accelerator Performance. Proceedings of the 7th International Particle Accelerator Conference (IPAC 2016), Busan, Korea."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.nima.2017.07.048","article-title":"Free-electron laser spectrum evaluation and automatic optimization","volume":"871","author":"Bruchon","year":"2017","journal-title":"Nucl. Instrum. Methods Phys. Res. Sect. A Accel. Spectrom. Detect. Assoc. Equip."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.nima.2014.09.057","article-title":"OCELOT: A software framework for synchrotron light source and FEL studies","volume":"768","author":"Agapov","year":"2014","journal-title":"Nucl. Instrum. Methods Phys. Res. Sect. A Accel. Spectrom. Detect. Assoc. Equip."},{"key":"ref_10","unstructured":"McIntire, M., Ratner, D., and Ermon, S. (2016, January 25\u201329). Sparse Gaussian Processes for Bayesian Optimization. Proceedings of the Thirty-Second Conference on Uncertainty in Artificial Intelligence UAI, New York, NY, USA."},{"key":"ref_11","unstructured":"McIntire, M., Cope, T., Ratner, D., and Ermon, S. (2016, January 8\u201313). Bayesian optimization of FEL performance at LCLS. Proceedings of the 7th International Particle Accelerator Conference (IPAC 2016), Busan, Korea."},{"key":"ref_12","unstructured":"Agapov, I., Geloni, G., and Zagorodnov, I. (2015, January 3\u20138). Statistical optimization of FEL performance. Proceedings of the 6th International Particle Accelerator Conference (IPAC 2015), Richmond, VA, USA."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1038\/s41586-018-0361-2","article-title":"Machine learning at the energy and intensity frontiers of particle physics","volume":"560","author":"Radovic","year":"2018","journal-title":"Nature"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"112802","DOI":"10.1103\/PhysRevAccelBeams.21.112802","article-title":"Machine learning-based longitudinal phase space prediction of particle accelerators","volume":"21","author":"Emma","year":"2018","journal-title":"Phys. Rev. Accel. Beams"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"044601","DOI":"10.1103\/PhysRevAccelBeams.23.044601","article-title":"Machine learning for orders of magnitude speedup in multiobjective optimization of particle accelerator systems","volume":"23","author":"Edelen","year":"2020","journal-title":"Phys. Rev. Accel. Beams"},{"key":"ref_16","unstructured":"Fol, E., de Portugal, J.C., Franchetti, G., and Tom\u00e1s, R. (2019, January 19\u201324). Optics corrections using Machine Learning in the LHC. Proceedings of the 2019 International Particle Accelerator Conference, Melbourne, Australia."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"093001","DOI":"10.1103\/PhysRevAccelBeams.22.093001","article-title":"Operational results on the fully automatic LHC collimator alignment","volume":"22","author":"Azzopardi","year":"2019","journal-title":"Phys. Rev. Accel. Beams"},{"key":"ref_18","unstructured":"M\u00fcller, R., Balzer, A., Baumg\u00e4rtel, P., Sauer, O., Hartmann, G., and Viefhaus, J. (2019, January 5\u201311). Modernization of experimental data taking at BESSY II. Proceedings of the 17th International Conference on Accelerator and Large Experimental Physics Control Systems, ICALEPCS2019, New York, NY, USA."},{"key":"ref_19","unstructured":"Edelen, A., Mayes, C., Bowring, D., Ratner, D., Adelmann, A., Ischebeck, R., Snuverink, J., Agapov, I., Kammering, R., and Edelen, J. (2018). Opportunities in machine learning for particle accelerators. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"124801","DOI":"10.1103\/PhysRevAccelBeams.23.124801","article-title":"Sample-efficient reinforcement learning for CERN accelerator control","volume":"23","author":"Kain","year":"2020","journal-title":"Phys. Rev. Accelerat. Beams"},{"key":"ref_21","unstructured":"Ramirez, L.V., Mertens, T., Mueller, R., Viefhaus, J., and Hartmann, G. (2019, January 5\u201311). Adding Machine Learning to the Analysis and Optimization Toolsets at the Light Source BESSY II. Proceedings of the 17th International Conference on Accelerator and Large Experimental Physics Control Systems, ICALEPCS2019, New York, NY, USA."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"878","DOI":"10.1109\/TNS.2016.2543203","article-title":"Neural networks for modeling and control of particle accelerators","volume":"63","author":"Edelen","year":"2016","journal-title":"IEEE Trans. Nucl. Sci."},{"key":"ref_23","unstructured":"Edelen, A.L., Edelen, J.P., RadiaSoft, L., Biedron, S.G., Milton, S.V., and van der Slot, P.J. (2017, January 4\u20139). Using Neural Network Control Policies For Rapid Switching Between Beam Parameters in a Free-Electron Laser. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS), Long Beach, CA, USA."},{"key":"ref_24","unstructured":"Edelen, A.L., Milton, S.V., Biedron, S.G., Edelen, J.P., and van der Slot, P.J.M. (2017). Using A Neural Network Control Policy For Rapid Switching between Beam Parameters in an FEL, Los Alamos National Lab. (LANL). Technical Report."},{"key":"ref_25","unstructured":"Hirlaender, S., Kain, V., and Schenk, M. (2019). New paradigms for tuning accelerators: Automatic performance optimization and first steps towards reinforcement learning at the CERN Low Energy Ion Ring. 2nd ICFA Workshop on Machine Learning for Charged Particle, Available online: https:\/\/indico.cern.ch\/event\/784769\/contributions\/3265006\/attachments\/1807476\/2950489\/CO-technical-meeting-_Hirlaender.pdf."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Bruchon, N., Fenu, G., Gaio, G., Lonza, M., Pellegrino, F.A., and Salvato, E. (2019, January 23\u201326). Toward the application of reinforcement learning to the intensity control of a seeded free-electron laser. Proceedings of the 2019 23rd International Conference on Mechatronics Technology (ICMT), Salerno, Italy.","DOI":"10.1109\/ICMECT.2019.8932150"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Bruchon, N., Fenu, G., Gaio, G., Lonza, M., O\u2019Shea, F.H., Pellegrino, F.A., and Salvato, E. (2020). Basic reinforcement learning techniques to control the intensity of a seeded free-electron laser. Electronics, 9.","DOI":"10.3390\/electronics9050781"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"122802","DOI":"10.1103\/PhysRevAccelBeams.23.122802","article-title":"Policy gradient methods for free-electron laser and terahertz source optimization and stabilization at the FERMI free-electron laser at Elettra","volume":"23","author":"Bruchon","year":"2020","journal-title":"Phys. Rev. Accel. Beams"},{"key":"ref_29","unstructured":"Hirlaender, S., and Bruchon, N. (2020). Model-free and Bayesian Ensembling Model-based Deep Reinforcement Learning for Particle Accelerator Control Demonstrated on the FERMI FEL. arXiv."},{"key":"ref_30","unstructured":"Li, W., and Todorov, E. (2004, January 25\u201328). Iterative linear quadratic regulator design for nonlinear biological movement systems. Proceedings of the First International Conference on Informatics in Control, Automation and Robotics, Set\u00fabal, Portugal."},{"key":"ref_31","unstructured":"Kain, V., Bruchon, N., Goddard, B., Hirlander, S., Madysa, N., Valentino, G., and Velotti, F. (2021, June 22). Sample-Efficient Reinforcement Learning for CERN Accelerator Control. The One World Charged ParticLe accElerator (OWLE) Colloquium & Seminar Series. Available online: https:\/\/drive.google.com\/file\/d\/1-OcdlK57VDNZnTOmkE_h28ZnTUqv7qza\/view."},{"key":"ref_32","unstructured":"\u00c5str\u00f6m, K.J., and Wittenmark, B. (2013). Computer-Controlled Systems: Theory and Design, Courier Corporation."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1049\/ip-cta:19960376","article-title":"Use of multilayer feedforward neural networks in identification and control of Wiener model","volume":"143","author":"Karim","year":"1996","journal-title":"IEE Proc. Control Theory Appl."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/S1474-6670(17)47737-8","article-title":"Neural networks in system identification","volume":"27","author":"Hjalmarsson","year":"1994","journal-title":"IFAC Proc. Vol."},{"key":"ref_35","unstructured":"N\u00f8rg\u00e5rd, P.M., Ravn, O., Poulsen, N.K., and Hansen, L.K. (2021, June 22). Neural Networks for Modelling and Control of Dynamic Systems\u2014A Practitioner\u2019s Handbook. Available online: https:\/\/orbit.dtu.dk\/en\/publications\/neural-networks-for-modelling-and-control-of-dynamic-systems-a-pr."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"J\u00e4ntschi, L., B\u00e1lint, D., and Bolboac\u0103, S.D. (2016). Multiple linear regressions by maximizing the likelihood under assumption of generalized Gauss-Laplace distribution of the error. Comput. Math. Methods Med., 2016.","DOI":"10.1155\/2016\/8578156"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"G\u00f3mez, Y.M., Gallardo, D.I., Le\u00e3o, J., and G\u00f3mez, H.W. (2020). Extended exponential regression model: Diagnostics and application to mineral data. Symmetry, 12.","DOI":"10.3390\/sym12122042"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Mzyk, G. (2014). Wiener System. Combined Parametric-Nonparametric Identification of Block-Oriented Systems, Springer International Publishing.","DOI":"10.1007\/978-3-319-03596-3"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Lewis, F.L., Vrabie, D., and Syrmos, V.L. (2012). Optimal Control, John Wiley & Sons.","DOI":"10.1002\/9781118122631"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Borrelli, F., Bemporad, A., and Morari, M. (2017). Predictive Control for Linear and Hybrid Systems, Cambridge University Press.","DOI":"10.1017\/9781139061759"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1109\/TIV.2019.2904385","article-title":"Autonomous driving motion planning with constrained iterative LQR","volume":"4","author":"Chen","year":"2019","journal-title":"IEEE Trans. Intell. Veh."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/12\/7\/262\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:24:38Z","timestamp":1760163878000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/12\/7\/262"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,26]]},"references-count":41,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2021,7]]}},"alternative-id":["info12070262"],"URL":"https:\/\/doi.org\/10.3390\/info12070262","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,26]]}}}