{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T12:39:54Z","timestamp":1770295194582,"version":"3.49.0"},"posted":{"date-parts":[[2026]]},"group-title":"SSRN","reference-count":52,"publisher":"Elsevier BV","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>This work presents symbolic regression as a route to compress nonlinear model predictive control (NMPC) into an explicit, deployable control law for resource-limited industrial hardware. The key barrier is the limited memory and processing power of programmable logic controllers (PLCs), which makes on-board real-time optimization impractical. Unseeded batch cooling crystallization of paracetamol in ethanol was used as a case study. First, a detailed population balance model (PBM) was embedded in an NMPC to generate closed-loop trajectories for representative operating scenarios. Symbolic regression was then applied to the resulting data to identify an algebraic mapping from temperature, supersaturation, and crystal size and mass tracking errors to the next temperature set-point. The learned expression was compact, interpretable, and PID-like, with gain scheduling and only basic arithmetic operations. Parameter uncertainty was quantified via confidence regions obtained from statistical analysis of the regression. Simulations over parameters within these regions showed that the symbolic regression controller (SRC) maintained satisfactory closed-loop performance across all statistically plausible settings, thereby inheriting robustness from the underlying NMPC in a data-driven manner. The SRC was implemented on an Allen-Bradley Micro 870 PLC at typical scan-cycle rates as a Structured Text function block and evaluated in a hardware-in-the-loop setup, where the PBM ran on a host computer and exchanged measurements and set-points with the PLC via Modbus\/TCP. Across multiple scenarios, the PLC-based SRC drove crystal size and mass close to their set-points using smooth temperature trajectories that respected actuator constraints. The approach delivered NMPC-level performance while avoiding online optimization.<\/jats:p>","DOI":"10.2139\/ssrn.6178786","type":"posted-content","created":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T21:38:02Z","timestamp":1770241082000},"source":"Crossref","is-referenced-by-count":0,"title":["Symbolic Regression\u2013Based Robust Control of Batch Crystallization: Design and PLC Implementation"],"prefix":"10.2139","author":[{"given":"Fernando","family":"Arrais Romero Dias Lima","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1397-9628","authenticated-orcid":true,"given":"Erbet  Almeida","family":"Costa","sequence":"additional","affiliation":[]},{"given":"M. Enis","family":"Leblebici","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7297-3571","authenticated-orcid":true,"given":"Argimiro  Resende","family":"Secchi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1090-8958","authenticated-orcid":true,"given":"Maur\u0131\u0301cio","family":"Bezerra de Souza J\u00fanior","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0963-6449","authenticated-orcid":true,"given":"Idelfonso  B. R.","family":"Nogueira","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"1185","DOI":"10.1016\/j.rser.2016.01.025","article-title":"A review on the applications of programmable logic controllers (plcs)","volume":"60","author":"E R Alphonsus","year":"2016","journal-title":"Renewable and Sustainable Energy Reviews"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s12532-018-0139-4","article-title":"CasADi -A software framework for nonlinear optimization and optimal control","volume":"11","author":"J A E Andersson","year":"2019","journal-title":"Mathematical Programming Computation"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"89497","DOI":"10.1109\/ACCESS.2020.2990567","article-title":"Multi-objective optimization in python","volume":"8","author":"J Blank","year":"2020","journal-title":"IEEE Access"},{"issue":"2","key":"ref4","first-page":"80016","article-title":"Advanced control of crystallization processes","volume":"26","author":"R D Braatz","year":"2002","journal-title":"Annual Reviews in Control"},{"key":"ref5","first-page":"1","article-title":"Introduction to model predictive control","author":"E F Camacho","year":"2007","journal-title":"Model Predictive Control"},{"key":"ref6","author":"M Cranmer","year":"2023","journal-title":"Interpretable machine learning for science with pysr and symbolicregression"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1016\/j.powtec.2021.01.075","article-title":"An artificial neural network model applied to convert sucrose chord length distributions into particle size distributions","volume":"384","author":"C Crestani","year":"2021","journal-title":"Powder Technology"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1002\/btpr.3426","article-title":"Control strategy for biopharmaceutical production by model predictive control","volume":"40","author":"T Eslami","year":"2024","journal-title":"Biotechnology Progress"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1361","DOI":"10.1021\/acs.iecr.5b03635","article-title":"Data-driven modeling and dynamic programming applied to batch cooling crystallization","volume":"55","author":"D J Griffin","year":"2016","journal-title":"Industrial & Engineering Chemistry Research"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1016\/j.ces.2017.01.065","article-title":"Using mc plots for control of paracetamol crystallization","volume":"164","author":"D J Griffin","year":"2017","journal-title":"Chemical Engineering Science"},{"key":"ref11","author":"B Huyck","year":"2012","journal-title":"Towards online model predictive control on a programmable logic controller: Practical considerations. Mathematical Problems in Engineering"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1208","DOI":"10.1109\/JSYST.2014.2368129","article-title":"Toward dependable embedded model predictive control","volume":"11","author":"T A Johansen","year":"2017","journal-title":"IEEE Systems Journal"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"1525","DOI":"10.1016\/B978-0-443-15274-0.50243-2","article-title":"Symbolic regression based interpretable data-driven softsensor for process quality control","volume":"52","author":"H Kay","year":"2023","journal-title":"33rd European Symposium on Computer Aided Process Engineering"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"2866","DOI":"10.1021\/acs.iecr.2c03465","article-title":"Modeling of nucleation, growth, and dissolution of paracetamol in ethanol solution for unseeded batch cooling crystallization with temperature-cycling strategy","volume":"62","author":"Y Kim","year":"2023","journal-title":"Industrial & Engineering Chemistry Research"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"4917","DOI":"10.1021\/ie701706v","article-title":"Modelling of the batch sucrose crystallization kinetics using artificial neural networks: Comparison with conventional regression analysis","volume":"47","author":"K V Kumar","year":"2008","journal-title":"Industrial & Engineering Chemistry Research"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"4060","DOI":"10.1021\/acs.iecr.6b04914","article-title":"Modeling of nucleation and growth kinetics for unseeded batch cooling crystallization","volume":"56","author":"H Li","year":"2017","journal-title":"Industrial & Engineering Chemistry Research"},{"key":"ref17","article-title":"a. Applications of machine learning for modeling and advanced control of crystallization processes: Developments and perspectives","volume":"14","author":"F A R Lima","journal-title":"Digital Chemical Engineering"},{"key":"ref18","first-page":"31","volume":"58","author":"F A R Lima","year":"2024","journal-title":"Controlling paracetamol unseeded batch crystallization with nmpc and inverse model"},{"key":"ref19","article-title":"Interpretable and uncertainty-aware machine learning for trustworthy prediction in batch crystallization","volume":"215","author":"F A R Lima","year":"2025","journal-title":"Chemical Engineering and Processing -Process Intensification"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1021\/acs.cgd.3c01027","article-title":"Statistical analyses of a population balance model of a batch crystallization process","volume":"24","author":"F A R D Lima","year":"2024","journal-title":"Crystal Growth & Design"},{"key":"ref21","article-title":"Influence of estimators and numerical approaches on the implementation of nmpcs","volume":"11","author":"F A R D Lima","year":"2023","journal-title":"Processes"},{"key":"ref22","article-title":"Experimental nonlinear model predictive control of crystal size and yield in batch cooling crystallization enabled by soft sensor and symbolic-based calibration model","author":"F A R D Lima","year":"2025","journal-title":"Industrial & Engineering Chemistry Research"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"19613","DOI":"10.1021\/acs.iecr.4c02060","article-title":"Neural network inverse model controllers for paracetamol unseeded batch cooling crystallization","volume":"63","author":"F A R D Lima","year":"2024","journal-title":"Industrial & Engineering Chemistry Research"},{"key":"ref24","article-title":"Development of a recurrent neural networks-based nmpc for controlling the concentration of a crystallization process","volume":"5","author":"F A R D Lima","year":"2022","journal-title":"Digital Chemical Engineering"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"5374","DOI":"10.1021\/acs.cgd.3c01251","article-title":"Recent Advances in the Application of Machine Learning to Crystal Behavior and Crystallization Process Control","volume":"24","author":"M Lu","year":"2024","journal-title":"Crystal Growth & Design"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1016\/j.seppur.2022.122668","article-title":"Handling model uncertainty in control of a pressure swing adsorption unit for syngas purification: A multi-model zone control scheme-based robust model predictive control strategy","volume":"306","author":"M A Martins","year":"2023","journal-title":"Separation and Purification Technology"},{"key":"ref27","article-title":"A plc-embedded implementation of a modified takagi-sugeno-kang-based mpc to control a pressure swing adsorption process","volume":"12","author":"T P G Mendes","year":"2024","journal-title":"Processes"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.118369","article-title":"A new takagisugeno-kang model-based stabilizing explicit mpc formulation: An experimental case study with implementation embedded in a plc","volume":"210","author":"T P G Mendes","year":"2022","journal-title":"Expert Systems with Applications"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"1188","DOI":"10.1109\/TCST.2011.2160945","article-title":"Nonlinear model-based control of a semi-industrial batch crystallizer using a population balance modeling framework","volume":"20","author":"A Mesbah","year":"2012","journal-title":"IEEE Transactions on Control Systems Technology"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"9515","DOI":"10.1021\/acs.iecr.3c00739","article-title":"Modeling and predictive control of cooling crystallization of potassium sulfate by dynamic image analysis: Exploring phenomenological and machine learning approaches","volume":"62","author":"M G F Moraes","year":"2023","journal-title":"Industrial & Engineering Chemistry Research"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.arcontrol.2020.04.016","article-title":"Model predictive control design for linear parameter varying systems: A survey","volume":"49","author":"M M Morato","year":"2020","journal-title":"Annual Reviews in Control"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1146\/annurev-chembioeng-062011-081043","article-title":"Advances and New Directions in Crystallization Control","volume":"3","author":"Z K Nagy","year":"2012","journal-title":"Annual Review of Chemical and Biomolecular Engineering"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"1245","DOI":"10.1021\/ie060637c","article-title":"Determination of the kinetic parameters for the crystallization of paracetamol from water using metastable zone width experiments","volume":"47","author":"Z K Nagy","year":"2008","journal-title":"Industrial & Engineering Chemistry Research"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1016\/j.cej.2019.123412","article-title":"A new formulation for symbolic regression to identify physico-chemical laws from experimental data","volume":"387","author":"P Neumann","year":"2020","journal-title":"Chemical Engineering Journal"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2019.106664","article-title":"A robustly model predictive control strategy applied in the control of a simulated industrial polyethylene polymerization process","volume":"133","author":"I B Nogueira","year":"2020","journal-title":"Computers & Chemical Engineering"},{"key":"ref36","doi-asserted-by":"crossref","DOI":"10.1002\/aic.18333","article-title":"Data-driven identification of crystallization kinetics","volume":"70","author":"B W Nyande","year":"2024","journal-title":"AIChE Journal"},{"key":"ref37","first-page":"219","article-title":"A robust model predictive controller applied to a pressure swing adsorption process: An analysis based on a linear model mismatch","volume":"54","author":"P H Oliveira","year":"2021","journal-title":"th IFAC Symposium on Advanced Control of Chemical Processes ADCHEM 2021"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1016\/j.cherd.2020.08.032","article-title":"Comprehensive evaluation of a data driven control strategy: Experimental application to a pharmaceutical crystallization process","volume":"163","author":"M Oner","year":"2020","journal-title":"Chemical Engineering Research and Design"},{"key":"ref39","journal-title":"Pymodbus: A full Modbus protocol implementation"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1016\/S0967-0661(02)00186-7","article-title":"A survey of industrial model predictive control technology","volume":"11","author":"S Qin","year":"2003","journal-title":"Control Engineering Practice"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"19030","DOI":"10.1021\/acs.iecr.4c02104","article-title":"Interpretable scientific machine learning approach for correcting phenomenological models: Methodology validation on an esp prototype","volume":"63","author":"C M Rebello","year":"2024","journal-title":"Industrial & Engineering Chemistry Research"},{"key":"ref42","author":"C M Rebello","year":"2025","journal-title":"Offset-free robust nonlinear control using data-driven model: A nonlinear multi-model computationally efficient approach"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1016\/j.ces.2023.119223","article-title":"Efficient hybrid modeling and sorption model discovery for non-linear advection-diffusion-sorption systems: A systematic scientific machine learning approach","volume":"282","author":"V V Santana","year":"2023","journal-title":"Chemical Engineering Science"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"1327","DOI":"10.1007\/s00170-021-07682-3","article-title":"Review on model predictive control: An engineering perspective","volume":"117","author":"M Schwenzer","year":"2021","journal-title":"The International Journal of Advanced Manufacturing Technology"},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.1002\/aic.18356","article-title":"Machine learning meets process control: Unveiling the potential of lstmc","volume":"70","author":"N Sitapure","year":"2024","journal-title":"AIChE Journal"},{"key":"ref46","article-title":"Multi-objective optimization based nonlinear model predictive control of seeded cooling crystallization process with application to form l-glutamic acid","volume":"299","author":"F Sun","year":"2024","journal-title":"Chem. Eng. Sci"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1016\/B978-0-12-818634-3.50213-7","article-title":"Real-time feasible model-based crystal size and shape control of crystallization processes","volume":"46","author":"B Szilagyi","year":"2019","journal-title":"29th European Symposium on Computer Aided Process Engineering"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1016\/j.ces.2018.09.032","article-title":"Experimental implementation of a quality-by-control (qbc) framework using a mechanistic pbm-based nonlinear model predictive control involving chord length distribution measurement for the batch cooling crystallization of l-ascorbic acid","volume":"195","author":"B Szil\ufffdgyi","year":"2019","journal-title":"Chem. Eng. Sci"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"732","DOI":"10.1016\/j.conengprac.2011.04.001","article-title":"Efficient suboptimal parametric solutions to predictive control for plc applications","volume":"19","author":"G Valencia-Palomo","year":"2011","journal-title":"Control Engineering Practice"},{"key":"ref50","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1557\/mrc.2019.85","article-title":"Symbolic regression in materials science","volume":"9","author":"Y Wang","year":"2019","journal-title":"MRS Communications"},{"key":"ref51","doi-asserted-by":"crossref","first-page":"13006","DOI":"10.1021\/acs.chemrev.2c00141","article-title":"Applications of artificial intelligence and machine learning algorithms to crystallization","volume":"122","author":"C Xiouras","year":"2022","journal-title":"Chemical Reviews"},{"key":"ref52","doi-asserted-by":"crossref","DOI":"10.1002\/aic.17815","article-title":"Online learning-based predictive control of crystallization processes under batch-to-batch parametric drift","volume":"68","author":"Y Zheng","year":"2022","journal-title":"AIChE Journal"}],"container-title":[],"original-title":[],"deposited":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T21:41:16Z","timestamp":1770241276000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ssrn.com\/abstract=6178786"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":52,"URL":"https:\/\/doi.org\/10.2139\/ssrn.6178786","relation":{},"subject":[],"published":{"date-parts":[[2026]]},"subtype":"preprint"}}