Modeling and simulation of xylitol production in bioreactor by Debaryomyces nepalensis NCYC 3413 using unstructured and artificial neural network models

Pappu, J. Sharon Mano; Gummadi, Sathyanarayana N.

doi:10.1016/j.biortech.2016.08.097

Cited by 23 publications

(16 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As summarized in Table 3, many ANN models have been applied in bioprocesses and have achieved success in the recent past (Ahmad, Crowley, Marina, & Jha, 2016; Bhattacharya, Dinesh, Dhanarajan, Sen, & Mishra, 2017; Hosseinzadeh et al, 2020; Liyanaarachchi, Nishshanka, Nimarshana, Ariyadasa, & Attalage, 2020; Pappu & Gummadi, 2016). Their remarkable feature was that the multiple related parameters were set as input variables to develop the ANN model and predict the output variables.…”

Section: Resultsmentioning

confidence: 99%

A robust soft sensor to monitor 1,3‐propanediol fermentation process by Clostridium butyricum based on artificial neural network

Zhang

Zhu

Zhuang

et al. 2020

Biotech & Bioengineering

View full text Add to dashboard Cite

With the aggravation of environmental pollution and energy crisis, the sustainable microbial fermentation process of converting glycerol to 1,3-propanediol (1,3-PDO) has become an attractive alternative. However, the difficulty in the online measurement of glycerol and 1,3-PDO creates a barrier to the fermentation process and then leads to the residual glycerol and therefore, its wastage. Thus, in the present study, the four-input artificial neural network (ANN) model was developed successfully to predict the concentration of glycerol, 1,3-PDO, and biomass with high accuracy. Moreover, an ANN model combined with a kinetic model was also successfully developed to simulate the fed-batch fermentation process accurately. Hence, a soft sensor from the ANN model based on NaOH-related parameters has been successfully developed which cannot only be applied in software to solve the difficulty of glycerol and 1,3-PDO online measurement during the industrialization process, but also offer insight and reference for similar fermentation processes. K E Y W O R D S 1, 3-propanediol, artificial neural network, Clostridium butyricum, soft sensor 1 | INTRODUCTION 1,3-Propanediol (1,3-PDO), an important chemical also used as a biochemical raw material, has been used for the synthesis of polymers, such as polytrimethylene terephthalate (PTT) and polytrimethylene ether glycol, and is endowed with numerous exceptional characteristics, such as good elasticity, inherent stain resistance, and low static

show abstract

Section: Resultsmentioning

confidence: 99%

A robust soft sensor to monitor 1,3‐propanediol fermentation process by Clostridium butyricum based on artificial neural network

Zhang

Zhu

Zhuang

et al. 2020

Biotech & Bioengineering

View full text Add to dashboard Cite

show abstract

“…Moreover, other studies reported that the woody biomass itself has a buffering effect due to the presence of mineral salts in the structure of wood. 20 Based on our previous publications, the experiments were carried out at three temperatures: 180, 190 and 200 °C for 5, 10 and 15 min residence time for each temperature. 21,30 Figure 2 presents the composition of the solid fraction recovered after autohydrolysis pretreatments as a function of the severity factor.…”

Section: Results and Discussion Autohydrolysis Pretreatment Of Woodmentioning

confidence: 99%

“…The information from the hidden layer is processed and then transmitted to the output layer. 20,29,30 The temperature and time parameters are independent variables. In this study, two methods were used: back-propagation and a hybrid method.…”

Section: Statistical Analysis By Adaptive Neural Fuzzy Interference Smentioning

confidence: 99%

“…The ANNs function like a human brain, which has the capability of learning the information required via a series of input (dependent variables) and output (dependent variables) data. 20,21 Akkaya 22 used the ANFIS based prediction model for determining the biomass heating value (fixed carbon, ash and volatile matter) using proximate analysis components. In this study, three methods (sub-clustering, grid partition and fuzzy interference system) were used for the prediction model and the performance prediction of ANFIS indicated very good precision.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bioethanol Production From Abies Alba Wood Using Adaptive Neural Fuzzy Interference System Mathematical Modeling

Șenilă¹,

Costiug²,

Becze³

et al. 2020

Cellulose Chem. Technol.

View full text Add to dashboard Cite

This study investigates bioethanol production from Abies alba wood. The wood was first autohydrolysed, then delignified and the remaining cellulose was used as substrate for simultaneous saccharification and fermentation processes. The influence of temperature (180, 190 and 200 °C) and pretreatment time (5, 10 and 15 min) on the fermentation medium products was studied. The maximal bioethanol content (52.0 g L -1 ) was obtained at a pretreatment temperature of 190 °C and pretreatment time of 10 min. The enzymatic hydrolysis and fermentation temperature was 38 °C for 72 h. The untreated, autohydrolysed and delignified wood was characterized by reflected light microscopy for morphological structure identification. The adaptive network-based fuzzy interference model (ANFIS) and the Gaussian membership function were used to reproduce the experimental results obtained for complete characterization of the wood fermentation broth. The proposed model uses two input variables (temperature and reaction time) and one output parameter based on two intelligent methods: back-propagation and a hybrid method. The hybrid intelligent method has good accuracy (99.2-100.0%) and correlation coefficient (0.998-1). The fermentation broth contains a mixture of bioethanol and secondary by-products, including acids, alcohols, aldehydes, ketones and esters. A maximum of 5.2 g bioethanol can be obtained from 100 g of woody biomass after autohydrolysisdelignification-SSF process.

show abstract

“…Charaniya et al (2010) identified several process parameters with strong associations to outcomes for the manufacturing of recombinant proteins using support vector machines. Caschera et al (2011) successfully increased the yield of their cell-free protein synthesis process by 350% via designing experimental conditions using artificial neural networks (ANNs), which were recently also applied to find the optimal harvest time for xylitol production by Pappu and Gummadi (2016). Others have looked at maximizing protein production by identifying and optimizing key factors in the fermentation process, also using ANNs (Sinha et al, 2014;Amiri et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

Prediction of Human Induced Pluripotent Stem Cell Cardiac Differentiation Outcome by Multifactorial Process Modeling

Williams

Löbel

Finklea

et al. 2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Human cardiomyocytes (CMs) have potential for use in therapeutic cell therapy and high-throughput drug screening. Because of the inability to expand adult CMs, their large-scale production from human pluripotent stem cells (hPSC) has been suggested. Significant improvements have been made in understanding directed differentiation processes of CMs from hPSCs and their suspension culture-based production at chemically defined conditions. However, optimization experiments are costly, timeconsuming, and highly variable, leading to challenges in developing reliable and consistent protocols for the generation of large CM numbers at high purity. This study examined the ability of data-driven modeling with machine learning for identifying key experimental conditions and predicting final CM content using data collected during hPSC-cardiac differentiation in advanced stirred tank bioreactors (STBRs). Through feature selection, we identified process conditions, features, and patterns that are the most influential on and predictive of the CM content at the process endpoint, on differentiation day 10 (dd10). Process-related features were extracted from experimental data collected from 58 differentiation experiments by feature engineering. These features included data continuously collected online by the bioreactor system, such as dissolved oxygen concentration and pH patterns, as well as offline determined data, including the cell density, cell aggregate size, and nutrient concentrations. The selected features were used as inputs to construct models to classify the resulting CM content as being "sufficient" or "insufficient" regarding pre-defined thresholds. The models built using random forests and Gaussian process modeling predicted insufficient CM content for a differentiation process with 90% accuracy and precision on dd7 of the protocol and with 85% accuracy and 82% precision at a substantially earlier stage: dd5. These models provide insight into potential key factors affecting hPSC cardiac differentiation to aid in selecting future experimental conditions and can predict the final CM content at earlier

show abstract

Modeling and simulation of xylitol production in bioreactor by Debaryomyces nepalensis NCYC 3413 using unstructured and artificial neural network models

Cited by 23 publications

References 37 publications

A robust soft sensor to monitor 1,3‐propanediol fermentation process by Clostridium butyricum based on artificial neural network

A robust soft sensor to monitor 1,3‐propanediol fermentation process by Clostridium butyricum based on artificial neural network

Bioethanol Production From Abies Alba Wood Using Adaptive Neural Fuzzy Interference System Mathematical Modeling

Prediction of Human Induced Pluripotent Stem Cell Cardiac Differentiation Outcome by Multifactorial Process Modeling

Contact Info

Product

Resources

About