Artificial neural networks: applications in chemical engineering

Pirdashti, Mohsen; Curteanu, Silvia; Kamangar, M. Hashemi; Hassim, Mimi Haryani; Khatami, Mohammad Amin

doi:10.1515/revce-2013-0013

Cited by 98 publications

(52 citation statements)

References 116 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The simulation results provided necessary information about the plant for the urban energy coordination system. Recently, Pirdashti et al (2013) presented a review on the application of neural networks in chemical engineering. They covered the use of ANN and evolutionary algorithms in fuels, energy, environment, health, safety, biotechnology, polymers, pharmaceutical, nanotechnology, and mineral industrial applications by reviewing 717 papers.…”

Section: Mass Balancementioning

confidence: 99%

Modeling, identification, and control of coal-fired thermal power plants

Chandrasekharan

Panda

Swaminathan³

2014

Reviews in Chemical Engineering

View full text Add to dashboard Cite

The major portion of total captive power comes from thermal power from coal, oil, natural gas, etc., of which coal-fired units contribute 41% of global electricity. The overall efficiency of such power plants is 33% due to variations in power plant design, use of wide fuel ranges, different steam turbines, and lack in modeling and control configurations. To improve this efficiency, knowledge on material and energy flows across subsystems, including fuel handling, boiler, turbine, and air management need to be known properly. In addition, there is a widespread lack in measurement and instrumentation systems in power plants across the fleet and operators. This scenario makes the operational adjustments more difficult. Again, the strictness in environmental compliances (sulfur and nitrogen components) is met at the cost of limiting thermal efficiency. Moreover, to comply with faster load change, less fuel consumption and more efficient supercritical boilers have been studied. Hence, to improve the efficiency level, more research starting from the state-ofthe-art review on modeling, identification, and control methods of coal-fired boilers and the integrated plant is aimed in this work. This will also address the issue of global climate change and reduction in emission of greenhouse gases.

show abstract

Section: Mass Balancementioning

confidence: 99%

Modeling, identification, and control of coal-fired thermal power plants

Chandrasekharan

Panda

Swaminathan³

2014

Reviews in Chemical Engineering

View full text Add to dashboard Cite

show abstract

“…The methods then address how to sample more efficiently along a predefined collective variable space. Interesting work in these areas has also included the use of artificial intelligence methodologies [41,42] to approximate the high dimensional statistics necessary and other stochastic processes including Markov models. Equilibrium simulations [43] have consistently improved with better forcefields, differing levels of resolution, algorithmic and hardware improvements allowing for deeper searches of the conformational space.…”

Section: Introductionmentioning

confidence: 99%

Addressing the Embeddability Problem in Transition Rate Estimation

Goolsby

Moradi

2019

Preprint

View full text Add to dashboard Cite

Markov State Models (MSM) and related techniques have gained significant traction as a tool for analyzing and guiding molecular dynamics simulations due to their ability to extract structural, thermodynamic, and kinetic information on proteins using computationally feasible simulations. Here, we revisit the common practice in extracting the thermodynamic and kinetic information from the empirical transition matrix. We propose to build a rate/generator matrix from the empirical transition matrix to provide an alternative approach for estimating both thermodynamic and kinetic quantities. We also discuss a fundamental issue with this approach, known as the embeddability problem and the ways to address this issue. We use a one-dimensional toy model to show the workings of the proposed methods. We also show that the common method of estimating the rates based on the eigendecomposition and our proposed method based on the rate matrix are complementary in that they can potentially provide an upper and a lower limit for transition rates.

show abstract

“…Although many signs of progress have been made in the development of hardware sensors, there are still some uncertainties about the robustness of these sensors for biomass measurement – especially in large‐scale, long‐term runs. As an alternative, soft sensors have gained significant attention for online monitoring and control of the critical variables in the fermentation process …”

Section: Introductionmentioning

confidence: 99%

“…As an alternative, soft sensors have gained significant attention for online monitoring and control of the critical variables in the fermentation process. 40,[43][44][45] Regarding soft sensors, implementing solely mechanistic modeling for optimization and control of fed-batch processes is often challenging and sometimes impossible. This is mainly because, in addition to the general complexity of metabolic mechanisms of microorganisms, the fed-batch fermentation process, owing to high variation with respect to time, is a highly dynamic and nonlinear process, which makes the mathematical description very complicated.…”

Section: Introductionmentioning

confidence: 99%

Comparative study of μ‐stat methanol feeding control in fed‐batch fermentation of Pichia pastoris producing HBsAg: an open‐loop control versus recurrent artificial neural network‐based feedback control

Beiroti

Hosseini

Aghasadeghi

et al. 2019

J of Chemical Tech & Biotech

View full text Add to dashboard Cite

BACKGROUND In recent decades, artificial neural network (ANN) has been shown to be a robust and promising tool in monitoring and controlling bioprocess systems. In a previous study, the authors designed a highly accurate and precise recurrent neural network (RNN) for predicting the biomass amount of recombinant Pichia pastoris Mut+ producing intracellular hepatitis B surface antigen (HBsAg) during fed‐batch methanol fermentation. In the current work, the aim was to compare the production efficiency of HBsAg between conventional predefined μ‐stat methanol feeding control (open‐loop control) – already established in large‐scale production – and methanol feeding based on a μ‐stat feedback control system using RNN. For this purpose, for each methanol feeding strategy, bench‐scale, fed‐batch fermentation processes were carried out twice. RESULTS According to the results, in contrast to the established μ‐stat predefined feeding strategy (open‐loop), the deviation of specific growth rate and biomass in μ‐stat feedback control based on RNN was negligible. Also, in the suggested methanol feeding control strategy, the HBsAg titer, specific productivity and yield between the performed fed‐batch fermentations – unlike the conventional method – were approximately identical, with average values of 110.8 μg mL−1, 1.52 μg g−1 dry biomass and 0.34 μg g−1 MeOH respectively. CONCLUSION Comparing the biomass growth pattern and HBsAg production efficiency with the conventional μ‐stat predefined feeding in open‐loop control, the new proposed feeding control system illustrated significantly high process efficiency. This reliable control system based on ANN can have many applications in the biopharmaceutical industry for the control of process key parameters as well as for enhancing process efficiency. © 2019 Society of Chemical Industry

show abstract

Artificial neural networks: applications in chemical engineering

Cited by 98 publications

References 116 publications

Modeling, identification, and control of coal-fired thermal power plants

Modeling, identification, and control of coal-fired thermal power plants

Addressing the Embeddability Problem in Transition Rate Estimation

Comparative study of μ‐stat methanol feeding control in fed‐batch fermentation of Pichia pastoris producing HBsAg: an open‐loop control versus recurrent artificial neural network‐based feedback control

Contact Info

Product

Resources

About