Why Use Interactive Multi-Objective Optimization in Chemical Process Design?

Miettinen, Kaisa; Hakanen, Jussi

doi:10.1142/9789813148239_0006

Cited by 5 publications

(4 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our work using autoencoders suggests that tools like the autoencoders can identify perturbations and hence may be valuable in stochastic optimization of the classical process design in the field of bioprocess engineering. While the current paradigm of process design is based on throughput rate, process yield and product purity [ 45 ], with the novel combination of cytometric fingerprinting and machine learning like the demonstrated autoencoders, process engineers may be able to optimize the digesters in real time, bypassing conventional lab-pilot-operations route [ 46 ].…”

Section: Discussionmentioning

confidence: 99%

Machine learning analysis of microbial flow cytometry data from nanoparticles, antibiotics and carbon sources perturbed anaerobic microbiomes

Dhoble¹,

Lahiri²,

Bhalerao³

2018

J Biol Eng

View full text Add to dashboard Cite

BackgroundFlow cytometry, with its high throughput nature, combined with the ability to measure an increasing number of cell parameters at once can surpass the throughput of prevalent genomic and metagenomic approaches in the study of microbiomes. Novel computational approaches to analyze flow cytometry data will result in greater insights and actionability as compared to traditional tools used in the analysis of microbiomes. This paper is a demonstration of the fruitfulness of machine learning in analyzing microbial flow cytometry data generated in anaerobic microbiome perturbation experiments.ResultsAutoencoders were found to be powerful in detecting anomalies in flow cytometry data from nanoparticles and carbon sources perturbed anaerobic microbiomes but was marginal in predicting perturbations due to antibiotics. A comparison between different algorithms based on predictive capabilities suggested that gradient boosting (GB) and deep learning, i.e. feed forward artificial neural network with three hidden layers (DL) were marginally better under tested conditions at predicting overall community structure while distributed random forests (DRF) worked better for predicting the most important putative microbial group(s) in the anaerobic digesters viz. methanogens, and it can be optimized with better parameter tuning. Predictive classification patterns with DL (feed forward artificial neural network with three hidden layers) were found to be comparable to previously demonstrated multivariate analysis. The potential applications of this approach have been demonstrated for monitoring the syntrophic resilience of the anaerobic microbiomes perturbed by synthetic nanoparticles as well as antibiotics.ConclusionMachine learning can benefit the microbial flow cytometry research community by providing rapid screening and characterization tools to discover patterns in the dynamic response of microbiomes to several stimuli.Electronic supplementary materialThe online version of this article (10.1186/s13036-018-0112-9) contains supplementary material, which is available to authorized users.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine learning analysis of microbial flow cytometry data from nanoparticles, antibiotics and carbon sources perturbed anaerobic microbiomes

Dhoble¹,

Lahiri²,

Bhalerao³

2018

J Biol Eng

View full text Add to dashboard Cite

show abstract

“…Cut points usually consider the targets for the different aroma compounds and multi-objective optimization (MOO) is suitable to solve this problem. Solving a MOO problem involves a set of optimal points known as a non-dominated solution or Pareto front (PF), and its optimal decision variables are known as a Pareto set [36]. The distillation of JXX baijiu involves many objectives with aroma characters that need to be optimized simultaneously and these objectives may conflict with each other, i.e., the improvement of one objective leads to the deterioration of another objective.…”

Section: Jxx Baijiu Distillation Time Cut Point Selectionmentioning

confidence: 99%

Aroma Compound Changes in the Jiangxiangxing Baijiu Solid-State Distillation Process: Description, Kinetic Characters and Cut Point Selection

Gao,

Yang,

Jin

et al. 2024

Foods

View full text Add to dashboard Cite

Solid-state distillation is a distinctive process for extracting the baijiu aroma compounds that determine the flavor character of baijiu. In this study, the changes in various chemical properties of the aroma compounds in three classical Jiangxiangxing baijiu fermented grain distillation processes were analyzed. The changes in the aroma compounds in the instantaneous distillates were quantified and correlation analyzes were conducted. The results showed that the effect of the aroma compounds was greater than the differences between the fermented grains. Eleven representative aroma compounds were selected to develop the kinetic models describing two opposing changes. For the regulation of the Jiangxiangxing baijiu aroma compounds, their recovery rates were calculated using a kinetic model. A comprehensive comparison of the recovery rates of the characteristic aroma and other aroma compounds at different cut-off values revealed that the optimum recovery rate of the characteristic aroma of Jiangxiangxing baijiu 2,3,5,6-tetramethylpyrazine was 14.53% at cut-off values of 3.9 and 19.8 min. In this study, representative changes in the aroma compounds and the selection of cut-off values to regulate the baijiu distillation aroma were proposed.

show abstract

“…This is repeated many times requiring the decision maker's preferences in between solving two slightly different SOO problems. The interactive methods and their applications in CPE can be found in [87].…”

Section: Single Versus Multi-objective Approachmentioning

confidence: 99%

Multi-Objective Optimization Applications in Chemical Process Engineering: Tutorial and Review

2020

View full text Add to dashboard Cite

This tutorial and review of multi-objective optimization (MOO) gives a detailed explanation of the 5 steps to create, solve, and then select the optimum result. Unlike single-objective optimization, the fifth step of selection or ranking of solutions is often overlooked by the authors of papers dealing with MOO applications. It is necessary to undertake a multi-criteria analysis to choose the best solution. A review of the recent publications using MOO for chemical process engineering problems shows a doubling of publications between 2016 and 2019. MOO applications in the energy area have seen a steady increase of over 20% annually over the last 10 years. The three key methods for solving MOO problems are presented in detail, and an emerging area of surrogate-assisted MOO is also described. The objectives used in MOO trade off conflicting requirements of a chemical engineering problem; these include fundamental criteria such as reaction yield or selectivity; economics; energy requirements; environmental performance; and process control. Typical objective functions in these categories are described, selection/ranking techniques are outlined, and available software for MOO are listed. It is concluded that MOO is gaining popularity as an important tool and is having an increasing use and impact in chemical process engineering.

show abstract

Why Use Interactive Multi-Objective Optimization in Chemical Process Design?

Cited by 5 publications

References 67 publications

Machine learning analysis of microbial flow cytometry data from nanoparticles, antibiotics and carbon sources perturbed anaerobic microbiomes

Machine learning analysis of microbial flow cytometry data from nanoparticles, antibiotics and carbon sources perturbed anaerobic microbiomes

Aroma Compound Changes in the Jiangxiangxing Baijiu Solid-State Distillation Process: Description, Kinetic Characters and Cut Point Selection

Multi-Objective Optimization Applications in Chemical Process Engineering: Tutorial and Review

Contact Info

Product

Resources

About