Artificial Neural Network control of thermoelectrically-cooled microfluidics using computer vision based on IR thermography

Benjamin A. Rizkin, Karina Popovich, Ryan Hartman

Research output: Contribution to journalArticle

Abstract

High-speed and high-accuracy thermal control of reactors has always been of interest to chemical engineers. In this paper we present a new methodology for thermal control of a continuous-flow chemical reactor using non-contact IR thermography combined with computer vision and a predictive Artificial Neural Network. The system exhibits several key advantages over thermocouples and PID control including the ability to quantify and account for thermal diffusion in the system, to collect and process data very quickly and with high accuracy, to analyze the entire surface of the reactor, and to update its training based not only on the current thermal response, but also on external factors. We have constructed and validated such a system as well as shown improvements in its accuracy, rise time, settling time, set point tracking, and overshoot as compared to more traditional forms of thermal control, validating this as a possible approach for experimental and process control.

Original languageEnglish (US)
Pages (from-to)584-593
Number of pages10
JournalComputers and Chemical Engineering
Volume121
DOIs
StatePublished - Feb 2 2019

Fingerprint

Microfluidics
Computer vision
Neural networks
Chemical reactors
Thermal diffusion
Three term control systems
Thermocouples
Process control
Engineers
Hot Temperature

Keywords

  • Autonomous microfluidics
  • Machine learning
  • Neural networks
  • Process control
  • Process resiliency
  • Thermal control

ASJC Scopus subject areas

  • Chemical Engineering(all)
  • Computer Science Applications

Cite this

Artificial Neural Network control of thermoelectrically-cooled microfluidics using computer vision based on IR thermography. / Rizkin, Benjamin A.; Popovich, Karina; Hartman, Ryan.

In: Computers and Chemical Engineering, Vol. 121, 02.02.2019, p. 584-593.

Research output: Contribution to journalArticle

@article{1ed589a0cc214f908f662870acd97e9a,
title = "Artificial Neural Network control of thermoelectrically-cooled microfluidics using computer vision based on IR thermography",
abstract = "High-speed and high-accuracy thermal control of reactors has always been of interest to chemical engineers. In this paper we present a new methodology for thermal control of a continuous-flow chemical reactor using non-contact IR thermography combined with computer vision and a predictive Artificial Neural Network. The system exhibits several key advantages over thermocouples and PID control including the ability to quantify and account for thermal diffusion in the system, to collect and process data very quickly and with high accuracy, to analyze the entire surface of the reactor, and to update its training based not only on the current thermal response, but also on external factors. We have constructed and validated such a system as well as shown improvements in its accuracy, rise time, settling time, set point tracking, and overshoot as compared to more traditional forms of thermal control, validating this as a possible approach for experimental and process control.",
keywords = "Autonomous microfluidics, Machine learning, Neural networks, Process control, Process resiliency, Thermal control",
author = "Rizkin, {Benjamin A.} and Karina Popovich and Ryan Hartman",
year = "2019",
month = "2",
day = "2",
doi = "10.1016/j.compchemeng.2018.11.016",
language = "English (US)",
volume = "121",
pages = "584--593",
journal = "Computers and Chemical Engineering",
issn = "0098-1354",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Artificial Neural Network control of thermoelectrically-cooled microfluidics using computer vision based on IR thermography

AU - Rizkin, Benjamin A.

AU - Popovich, Karina

AU - Hartman, Ryan

PY - 2019/2/2

Y1 - 2019/2/2

N2 - High-speed and high-accuracy thermal control of reactors has always been of interest to chemical engineers. In this paper we present a new methodology for thermal control of a continuous-flow chemical reactor using non-contact IR thermography combined with computer vision and a predictive Artificial Neural Network. The system exhibits several key advantages over thermocouples and PID control including the ability to quantify and account for thermal diffusion in the system, to collect and process data very quickly and with high accuracy, to analyze the entire surface of the reactor, and to update its training based not only on the current thermal response, but also on external factors. We have constructed and validated such a system as well as shown improvements in its accuracy, rise time, settling time, set point tracking, and overshoot as compared to more traditional forms of thermal control, validating this as a possible approach for experimental and process control.

AB - High-speed and high-accuracy thermal control of reactors has always been of interest to chemical engineers. In this paper we present a new methodology for thermal control of a continuous-flow chemical reactor using non-contact IR thermography combined with computer vision and a predictive Artificial Neural Network. The system exhibits several key advantages over thermocouples and PID control including the ability to quantify and account for thermal diffusion in the system, to collect and process data very quickly and with high accuracy, to analyze the entire surface of the reactor, and to update its training based not only on the current thermal response, but also on external factors. We have constructed and validated such a system as well as shown improvements in its accuracy, rise time, settling time, set point tracking, and overshoot as compared to more traditional forms of thermal control, validating this as a possible approach for experimental and process control.

KW - Autonomous microfluidics

KW - Machine learning

KW - Neural networks

KW - Process control

KW - Process resiliency

KW - Thermal control

UR - http://www.scopus.com/inward/record.url?scp=85057595246&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057595246&partnerID=8YFLogxK

U2 - 10.1016/j.compchemeng.2018.11.016

DO - 10.1016/j.compchemeng.2018.11.016

M3 - Article

VL - 121

SP - 584

EP - 593

JO - Computers and Chemical Engineering

JF - Computers and Chemical Engineering

SN - 0098-1354

ER -