On-line biomass estimation in biosurfactant production process by Candida lipolytica UCP 988

Abstract

Biomass is an important variable in biosurfactant production process. However, such bioprocess variable, usually, is collected by sampling and determined by off-line analysis, with significant time delay. Therefore, simple and reliable on-line biomass estimation procedures are highly desirable. An artificial neural network model (ANN) is presented for the on-line estimation of biomass concentration, in biosurfactant production by Candida lipolytica UCP 988, as a nonlinear function of pH and dissolved oxygen. Several configurations were evaluated while developing the optimal ANN model. The optimal ANN model consists of one hidden layer with four neurons. The performance of the ANN was checked using experimental data. The results obtained indicate a very good predictive capacity for the ANN-based software sensor with values of R2 of 0.969 and RMSE of 0.021 for biomass concentration. Estimated biomass using the ANN was proved to be a simple, robust and accurate method.

Real-time monitoring and control of microbial bioprocesses with focus on the specific growth rate: current state and perspectives

“…ANN have a tremendous application potential, especially in industrial processes where an enormous amount of data is available for model training and validation. ANN have been extensively applied to estimate biomass (Desai et al 2005;Won and Yoon-Keun 2006;da Costa Albuquerque et al 2008) and substrate concentrations (Hocalar et al 2011) or oxygen uptake rate (Jenzsch et al 2006); however, probably due to the lack of offline values in sufficient number for training and validation, examples of real-time estimations of μ by ANN or similar methods are rare.…”

MONITORING OF BIOSURFACTANT PRODUCTION BY Bacillus subtilis USING BEET PEEL AS CULTURE MEDIUM VIA THE DEVELOPMENT OF A NEURAL SOFT-SENSOR IN AN ELECTRONIC SPREADSHEET

“…A neural model with a large set of parameters can cause overfitting, leading to large errors in performance for prediction. Small-size neural networks are important for real-time applications, due to their better generalization capability and less computational effort (Albuquerque et al, 2008). Thus, the developed neural model can be applied to predict dynamic behaviour in batch bioreactors for Kashkouli et al (2011) used ANN modelling in fermentation parameters for biosurfactant production by Bacillus subtilis using sugar cane molasses.…”

“…Sivapathasekaran et al (2010) developed a neural model to predict biosurfactant production, taking into account the four concentrations of the critical medium components glucose, urea, MgSO 4 , and SrCl 2 . Other ANN models were also developed by Singh et al (2008), Rahimi et al (2015), , Albuquerque et al (2008), Oroian (2015), , Fu et al (2013), Oladunjoye et al (2016) and others.…”

Sliding Mode Observer based Control for a Continuous Fermentation Process

“…Fermentation processes are known to be difficult to control but the benefits of successful control include reduced production costs and increased profit margins without compromising product quality which makes the problem of considerable interest to industry (Yamuna Rani and Ramachandra Rao, 1999, Fossas et al, 2001, da Costa Albuquerque et al, 2008, Veloso et al, 2009, Szederkenyi et al, 2002. The major obstacle to precise control is that the process itself involves living microorganisms that continually change.…”

“…However, some key parameters are not readily measurable with standard devices e.g. biomass concentration (da Costa Albuquerque et al, 2008, Jenzsch et al, 2006, Veloso et al, 2009. Online measurement may not be practical due to the lack of economically priced, reliable and sterilisable transducers (Veloso et al, 2009, Farza et al, 1999, Gonzalez et al, 2001, Dochain, 2003, Bastin and Van Impe, 1995.…”