A multi-feature recognition criterion for identification of thermally safe operating conditions for single kinetically-controlled reactions occurring in isoperibolic liquid-liquid semibatch reactors

Abstract Many criteria have been developed to date for thermal behavior identification for single kinetically controlled reactions occurring in isoperibolic liquid-liquid semibatch reactors (SBRs), the essence of which resides in the extraction and recognition of ‘features’ which can characterize different thermal behaviors; accordingly, thermal behavior identification may be regarded as a pattern recognition problem. Here, a novel multi-feature recognition (MFR) criterion was proposed based on the support vector machine (SVM) pattern recognition algorithm with a feature dimension of five, allowing the effective identification of four categories of thermal behaviors, namely IS (inherently safe), NI (non-ignition), TR (thermal runaway) and QFS (quick onset, fair conversion and smooth temperature condition). Subsequently, a modified generalized IS region was defined by introducing a threshold where the maximum temperature of synthesis reactions (MTSR) after cooling failure is equal to the maximum allowable temperature (MAT). The rationality of the proposed MFR criterion was verified by comparing with established criteria. Finally, a practical procedure based on the proposed criterion was presented, enabling the selection of optimum operating conditions with the desired productivity and thermal safety.

[1]  P C Bowes,et al.  Some aspects of the self-heating and ignition of solid cellulosic materials , 1961 .

[2]  Jacques Villermaux,et al.  Tendency modeling of semibatch reactors for optimization and control , 1986 .

[3]  Onder Aydemir,et al.  A polynomial fitting and k-NN based approach for improving classification of motor imagery BCI data , 2010, Pattern Recognit. Lett..

[4]  Fernanda Strozzi,et al.  On-Line Runaway Detection in Batch Reactors Using Chaos Theory Techniques. , 1999 .

[5]  Giuseppe Maschio,et al.  A general criterion to define runaway limits in chemical reactors , 2003 .

[6]  T. Qiu,et al.  Study on the esterification for ethylene glycol diacetate using supported ionic liquids as catalyst: Catalysts preparation, characterization, and reaction kinetics, process , 2015 .

[7]  Massimo Morbidelli,et al.  Parametric sensitivity and runaway in fixed-bed catalytic reactors , 1986 .

[8]  Dominique M. Roberge,et al.  Micro-reactor mixing unit interspacing for fast liquid-liquid reactions leading to a generalized scale-up methodology , 2018, Chemical Engineering Journal.

[9]  Massimo Morbidelli,et al.  Parametric sensitivity and runaway in tubular reactors , 1982 .

[10]  Renato Rota,et al.  Simple Monitoring of Semibatch Polymerization Processes: An Integrated Criterion , 2017 .

[11]  Marco Derudi,et al.  Topological criteria to safely optimize hazardous chemical processes involving consecutive reactions , 2010 .

[12]  Li Lin,et al.  Bilinear Grid Search Strategy Based Support Vector Machines Learning Method , 2014, Informatica.

[13]  Rim Saada,et al.  Causes and consequences of thermal runaway incidents—Will they ever be avoided? , 2015 .

[14]  A. Ralston.  Runge-Kutta methods with minimum error bounds , 1962 .

[15]  N. N. Semenov,et al.  Thermal Theory of Combustion and Explosion , 1942 .

[16]  Peter Hugo,et al.  Praxisorientierte Darstellung der thermischen Sicherheitsgrenzen für den indirekt gekühlten Semibatch-Reaktor , 1985 .

[17]  K. Roel Westerterp,et al.  Thermally Safe Operation of a Semibatch Reactor for Liquid-Liquid Reactions - Fast Reactions , 1991 .

[18]  G. Froment,et al.  Chemical Reactor Analysis and Design , 1979 .

[19]  Ertuğrul Çam,et al.  Forecasting electricity consumption: A comparison of regression analysis, neural networks and least squares support vector machines , 2015 .

[20]  Klaas R. Westerterp,et al.  Thermally safe operation of a semibatch reactor for liquid-liquid reactions. Slow reactions , 1990 .

[21]  L C van der Gaag,et al.  Constructing naive Bayesian classifiers for veterinary medicine: a case study in the clinical diagnosis of classical swine fever. , 2011, Research in veterinary science.

[22]  Francis Stoessel,et al.  Thermal Safety of Chemical Processes: Risk Assessment and Process Design , 2008 .

[23]  Enrique Velo,et al.  Safe operation of stirred-tank semibatch reactors subject to risk of thermal hazard , 2006 .

[24]  Ming Zeng,et al.  Improving Classification of Slow Cortical Potential Signals for BCI Systems With Polynomial Fitting and Voting Support Vector Machine , 2018, IEEE Signal Processing Letters.

[25]  Anca Dan,et al.  Derivation of optimal operating policies under safety and technological constraints for the acetoacetylation of pyrrole in a semi-batch catalytic reactor , 2011, Comput. Chem. Eng..

[26]  Steven J. Ruuth,et al.  Non-linear evolution using optimal fourth-order strong-stability-preserving Runge-Kutta methods , 2003, Math. Comput. Simul..

[27]  Lloyd N. Trefethen,et al.  Fourth-Order Time-Stepping for Stiff PDEs , 2005, SIAM J. Sci. Comput..

[28]  R. Gygax.  Chemical reaction engineering for safety , 1988 .

[29]  Wenshuai Bai,et al.  An adiabatic criterion for runaway detection in semibatch reactors , 2016 .

[30]  Dayou Liu,et al.  Evolving support vector machines using fruit fly optimization for medical data classification , 2016, Knowl. Based Syst..

[31]  L. Boucheron,et al.  PREDICTION OF SOLAR FLARE SIZE AND TIME-TO-FLARE USING SUPPORT VECTOR MACHINE REGRESSION , 2015, 1511.01941.

[32]  Peter Hugo,et al.  A comparison of the limits of safe operation of a SBR and a CSTR , 1986 .

[33]  Fernanda Strozzi,et al.  A general method for assessing the thermal stability of batch chemical reactors by sensitivity calculation based on Lyapunov exponents , 1994 .

[34]  Renato Rota,et al.  Kinetic-Free Safe Operation of Fine Chemical Runaway Reactions: A General Criterion , 2016 .

[35]  Herschel Rabitz,et al.  Parametric sensitivity and self-similarity in thermal explosion theory , 1992 .

[36]  Renato Rota,et al.  Kinetic-Free Safe Optimization of a Semibatch Runaway Reaction: Nitration of 4-Chloro Benzotrifluoride , 2016 .

[37]  Renato Rota,et al.  Temperature diagrams for preventing decomposition or side reactions in liquid–liquid semibatch reactors , 2006 .

[38]  Wei Jiang,et al.  k-Nearest Neighbor Classification over Semantically Secure Encrypted Relational Data , 2014, IEEE Transactions on Knowledge and Data Engineering.

[39]  Rui Wang,et al.  A new criterion to identify safe operating conditions for isoperibolic homogeneous semi-batch reactions , 2017 .

[40]  J. Adler,et al.  The critical conditions in thermal explosion theory with reactant consumption , 1964 .

[41]  Klaas R. Westerterp,et al.  The nitric acid oxidation of 2-octanol. A model reaction for multiple heterogeneous liquid-liquid reactions , 2000 .

[42]  Rainer Goebel,et al.  Fast Gaussian Naïve Bayes for searchlight classification analysis , 2017, NeuroImage.

[43]  K. R. Westerterp,et al.  Thermally safe operation of a cooled semi-batch reactor: slow liquid-liquid reactions , 1988 .

[44]  Marco Derudi,et al.  Topological Criterion To Safely Optimize Hazardous Chemical Processes Involving Arbitrary Kinetic Schemes , 2011 .

[45]  Kaveh Pahlavan,et al.  Enlighten Wearable Physiological Monitoring Systems: On-Body RF Characteristics Based Human Motion Classification Using a Support Vector Machine , 2016, IEEE Transactions on Mobile Computing.

[46]  Wenshuai Bai,et al.  Investigation into Maximum Temperature of Synthesis Reaction and Accumulation in Isothermal Semibatch Processes , 2015 .