ИСПОЛЬЗОВАНИЕ МЕТОДОВ МАШИННОГО ОБУЧЕНИЯ И ИСКУССТВЕННОГО ИНТЕЛЛЕКТА В ХИМИЧЕСКОЙ ТЕХНОЛОГИИ. ЧАСТЬ I

Виль Ришатович Нигматуллин, Николай Анатольевич Руднев

Аннотация


В работе рассмотрено применение методов машинного обучения и искусственного интеллекта для различных задач химической технологии, таких как моделирование, автоматизация и оптимизация процессов, контроль качества и безопасности, поиск новых соединений и катализаторов. Для данных целей были использованы искусственные нейронные сети, метод решающих деревьев, бустинг, регрессия, а также их комбинации. Работа разбита на две части. В первой части рассматриваются многокритериальная оптимизация; решение задач, связанных с поиском оптимальных путей реакций; предсказания параметров соединений и моделирование (создание цифровых двойников) процессов и аппаратов химической технологии.

Ключевые слова


машинное обучение;нейронные сети;глубокие нейронные сети;бустинг;решающие деревья;оптимизация;инструментарии машинного обучения;математическая модель;Big Data;цифровой двойник;machine learning;neural networks;deep neural networks;boosting;decision trees;optimization;machine learning tools;mathematical model;Big Data;digital twin;

Полный текст:

PDF

Литература


Fabry D.C. Online Monitoring and Analysis for Autonomous Continuous Flow Self-Optimizing Reactor Systems // React. Chem. Eng. 2016. No. 1. P. 129-133.

Sans V. Towards Dial-A-Molecule by Integrating Continuous Flow, Analytics and Self-Optimization // Chem. Soc. Rev. 2016. No. 45. P. 2032-2043.

Reizman B.J. Feedback in Flow for Accelerated Reaction Development // Acc. Chem. Res. 2016. No. 49. P. 1786-1789.

Schweidtmann A.M. Machine Learning Meets Continuous Flow Chemistry: Automated Optimization towards the Pareto Front of Multiple Objectives // Chemical Engineering Journal. 2018. No. 352. P. 277-282.

Skilton R.A. Real-Time Feedback Control Using Online Attenuated Total Reflection Fourier Transform Infrared (ATR FT-IR) Spectroscopy for Continuous Flow Optimization and Process Knowledge // Appl. Spectroscopy. 2013. No. 67. P. 1127-1131.

Sans V. A Self Optimizing Synthetic Organic Reactor System Using Real-Time In-Line NMR Spectroscopy // Chem. Sci. 2015. No. 6. P. 1258-1264.

Holmes N. Online Quantitative Mass Spectrometry for the Rapid Adaptive Optimization of Automated Flow Reactors // React. Chem. Eng. 2016. No. 1. P. 96-100.

McMullen J.P. An Automated Micro-Fluidic System for Online Optimization in Chemical Synthesis // Org. Process Res. Dev. 2010. No. 14. P. 1169-1176.

Parrott A.J. Self-Optimizing Continuous Reactions in Supercritical Carbon Dioxide // Angew. Chem. Int. Ed. 2011. No. 50. P. 3788-1392.

Holmes N. Self-Optimization of the Final Stage in the Synthesis of EGFR Kinase Inhibitor AZD9291 Using an Automated Flow Reactor // React. Chem. Eng. 2016. No. 1. P. 366-371.

Cortes-Borda D. Optimizing the Heck-Matsuda Reaction in Flow with a Constraint-Adapted Direct Search Algorithm // Org. Process Res. Dev. 2016. No. 20. P. 1979-1987.

Reizman B.J. Suzuki-Miyaura Cross-Coupling Optimization Enabled by Automated Feedback // React. Chem. Eng. 2016. No. 1. P. 658-666.

Reizman B.J. Simultaneous Solvent Screening and Reaction Optimization in Microliter Slugs // Chemical Communications. 2015. No. 51. P. 13290-13293.

Echtermeyer A. Selfoptimization and Model-Based Design of Experiments for Developing a C-H Activation Flow Process // Beilstein J. Org. Chem. 2017. No. 13. P. 150-163.

Skilton R.A. Remote-Controlled Experiments with Cloud Chemistry // Nat. Chem. 2015. No. 7. P. 1-5.

Houben C. Closed-Loop Multitarget Optimization for Discovery of New Emulsion Polymerization Recipes // Org. Process Res. Dev. 2015. No. 19. P. 1049-1053.

Peremezhney N. Combining Gaussian Processes, Mutual Information and a Genetic Algorithm for Multi-Target Optimization of Expensive-To-Evaluate Functions // Eng. Optimiz. 2014. No. 46. P. 1593-1607.

Fitzpatrick D.E. A Novel Internet-Based Reaction Monitoring, Control and Autonomous Self-Optimization Platform for Chemical Synthesis // Org. Process Res. Dev. 2016. No. 20. P. 386-394.

Helmdach D. A Multi‐Objective Optimization Including Results of Life Cycle Assessment in Developing Bio-Renewables-Based Processes // Chem. Sus. 2017. No. 10. pp. 3632-3643.

Shahriari B. Taking the Human out of the Loop: A Review of Bayesian Optimization // Proc. IEEE. 2016. No. 104. P. 148-175.

Boukouvala F. Global Optimization Advances in Mixed-Integer Nonlinear Programming, MINLP, and Constrained Derivative-Free Optimization, CDFO // Eur.J.Oper.Res. 2016. No. 252. P. 701-727.

Bradford E. Efficient Multiobjective Optimization Employing Gaussian Processes, Spectral Sampling and a Genetic Algorithm // J. Global Optim. 2018. No. 71. P. 407-438.

Moore J.S. Automated Multitrajectory Method for Reaction Optimization in a Microfluidic System using Online IR Analysis // Org. Process Res. Dev. 2012. No. 16. P. 1409-1415.

O’Brien A.G. Continuous Synthesis and Purification by Direct Coupling of a Flow Reactor with Simulated Moving-Bed Chromatography // Angew. Chem. Int. Ed. 2012. No. 51. P. 7028-7030.

Rasmussen C.E. Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning). MIT Press, 2005.

Zhang L. New Vistas in Chemical Product and Process Design // Rev. Chem. Biomol. 2016. No. 7. pp. 557-582.

Zhang L. Generic Mathematical Programming Formulation and Solution for Computer-Aided Molecular Design // Computers & Chemical Engineering. 2015. No. 78. P. 79-84.

Zhang L., Mao H., Liu L., Du J., Gani R. A Machine Learning Based Computer-aided Molecular Design/Screening Methodology for Fragrance Molecules // Computers and Chemical Engineering. 2018. Vol. 115. P. 295-308

Schneider N. Development of a Novel Fingerprint for Chemical Reactions and Its Application to Large-Scale Reaction Classification and Similarity // J. Chem. Inf. Model. 2015. No. 55. P. 39-53.

Warr W.A. A Short Review of Chemical Reaction Database Systems, Computer-aided Synthesis Design, reaction Prediction and Synthetic Feasibility // Mol. Inf. 2014. No. 33. P. 469-476.

Segler M. Planning Chemical Syntheses with Deep Neural Networks and Symbolic AI // Nature. 2018. No. 555. P. 604-610.

Gini A. Dehydrogenative Tempo-Mediated Formation of Unstable Nitrones: Easy Access to n-Carbamoyl Isoxazolines // Chemistry. 2015. No. 21. P. 12053-12060.

Segler M. Neural-Symbolic Machine Learning for Retrosynthesis and Reaction Prediction // Chemistry. 2017. No. 23. P. 5966-5971.

Marcou G. Expert System for Predicting Reaction Conditions: the Michael Reaction Case // J. Chem. Inf. Model. 2015. No. 55. Pp. 239-250.

Lake B.M. Building Machines That Learn and Think Like People // Behav. Brain Sci. 2016. No. 40. pp. 1-101.

Sierra M.A. Dead Ends and Detours en Route to Total Syntheses of the 1990s // Angew. Chem. Int. Ed. 2000. No. 39. pp. 1538-1559.

Segler M. Modelling Chemical Reasoning to Predict and Invent Reactions // Chemistry. 2017. No. 23. P. 6118-6128.

Peng Q. Computing Organic Stereo Selectivity – from Concepts to Quantitative Calculations and Predictions // Chem. Soc. Rev. 2016. No. 45. P. 6093-6107.

Lin A.I. Automatized Assessment of Protective Group Reactivity: a Step toward Big Reaction Data Analysis // J. Chem. Inf. Model. 2016. No. 56. P. 2140-2148.

Chen X. Prediction of Product Distribution and Bio-Oil Heating Value of Biomass Fast Pyrolysis // Chemical Engineering & Processing: Process Intensification. 2018. No. 130. P. 36-42.

Cao H.L. Prediction of Biochar Yield from Cattle Manure Pyrolysis via Least Squares Support Vector Machine Intelligent Approach // Bioresour. Technol. 2016. No. 202. P. 158-164.

Abdelnur P.V. Characterization of Bio-Oils from Different Pyrolysis Process Steps and Biomass using High-Resolution Mass Spectrometry // Energy Fuel. 2013. No. 27. Pp. 6646-6654.

Ly H.V. Fast Pyrolysis of macroalga Saccharina Japonica in a Bubbling Fluidized-Bed Reactor for Bio-Oil Production // Energy. 2015. No. 93. P. 1436-1446.

Wu S.R. Comparison of Oil-Tea Shell and Douglas-Fir Sawdust for the Production of Bio-Oils and Chars in a Fluidized-Bed Fast Pyrolysis System // Fuel. 2016. No. 175. P. 57-63.

Suttibak S. Production of Bio-Oil from Pine Sawdust by Rapid Pyrolysis in a Fluidized-Bed Reactor // Energy Sources Part A-Recovery Util. Environ. Effects. 2015. No. 37. P. 1440-1446.

Pattiya A. Bio-Oil Production via Fast Pyrolysis of Biomass Residues from Cassava Plants in a Fluidised-Bed Reactor // Bioresour. Technol. 2011. No. 102. P. 1959-1967.

Asset Performance Management (APM). URL: https://www.aspentech.com/en/products/apm/aspen-promv (дата обращения: 13.02.2019).

Schaub G. Biofuels for Automobiles – an Overview // Chem. Eng. Technol. 2008. No. 31. P. 721-729.

Lenz V. Smart Biomass Heat – Heat from Solid Biofuels as an Integral Part of a Future Energy System Based on Renewable // Chem. Eng. Technol. 2017. No. 40. P. 313-322.




DOI: http://dx.doi.org/10.17122/ogbus-2019-4-243-268

Ссылки

  • На текущий момент ссылки отсутствуют.