Browsing by Person "Yousefi-Darani, Abdolrahim"

Now showing 1 - 3 of 3

Development of software sensors for on-line monitoring of baker’s yeast fermentation process
(2021) Yousefi-Darani, Abdolrahim; Hitzmann, Bernd
Software sensors and bioprocess are well-established research areas which have much to offer each other. Under the perspective of the software sensors area, bioprocess can be considered as a broad application area with a growing number of complex and challenging tasks to be dealt with, whose solutions can contribute to achieving high productivity and high-quality products. Although throughout the past years in the field of software sensors and bioprocess, progress has been quick and with a high degree of success, there is still a lack of inexpensive and reliable sensors for on-line state and parameter estimation. Therefore, the primary objective of this research was to design an inexpensive measurement system for on-line monitoring of ethanol production during the backer’s yeast cultivation process. The measurement system is based on commercially available metal oxide semiconductor gas sensors. From the bioreactor headspace, samples are pumped past the gas sensors array for 10 s every five minutes and the voltage changes of the sensors are measured. The signals from the gas sensor array showed a high correlation with ethanol concentration during cultivation process. In order to predict ethanol concentrations from the data of the gas sensor array, a principal component regression (PCR) model was developed. For the calibration procedure no off-line sampling was used. Instead, a theoretical model of the process is applied to simulate the ethanol production at any given time. The simulated ethanol concentrations were used as reference data for calibrating the response of the gas sensor array. The obtained results indicate that the model-based calibrated gas sensor array is able to predict ethanol concentrations during the cultivation process with a high accuracy (root mean square error of calibration as well as the percentage error for the validation sets were below 0.2 gL-1 and 7 %, respectively). However the predicted values are only available every five minutes. Therefore, the following plan of the research goal was to implement an estimation method for continues prediction of ethanol as well as glucose, biomass and the growth rates. For this reason, two nonlinear extensions of the Kalman filter namely the extended Kalman filter (EKF) and the unscented Kalman filter (UKF) were implemented separately for state and parameter estimation. Both prediction methods were validated on three different cultivation with variability of the substrate concentrations. The obtained results showed that both estimation algorithms show satisfactory results with respect to estimation of concentrations of substrates 6 and biomass as well as the growth rate parameters during the cultivation. However, despite the easier implementation producer of the UKF, this method shows more accurate prediction results compared to the EKF prediction method. Another focus of this study was to design and implement an on-line monitoring and control system for the volume evaluation of dough pieces during the proofing process of bread making. For this reason, a software sensor based on image processing was designed and implemented for measuring the dough volume. The control system consists of a fuzzy logic controller which takes into account the estimated volume. The controller is designed to maintain the volume of the dough pieces similar to the volume expansion of a dough piece in standard conditions during the proofing process by manipulating the temperature of the proofing chamber. Dough pieces with different amounts of backer’s yeast added in the ingredients and in different temperature starting states were prepared and proofed with the supervision of the software sensor and the fuzzy controller. The controller was evaluated by means of performance criteria and the final volume of the dough samples. The obtained results indicate that the performance of the system is very satisfactory with respect to volume control and set point deviation of the dough pieces.
Generic chemometric models for metabolite concentration prediction based on Raman spectra
(2022) Yousefi-Darani, Abdolrahim; Paquet-Durand, Olivier; von Wrochem, Almut; Classen, Jens; Tränkle, Jens; Mertens, Mario; Snelders, Jeroen; Chotteau, Veronique; Mäkinen, Meeri; Handl, Alina; Kadisch, Marvin; Lang, Dietmar; Dumas, Patrick; Hitzmann, Bernd
Chemometric models for on-line process monitoring have become well established in pharmaceutical bioprocesses. The main drawback is the required calibration effort and the inflexibility regarding system or process changes. So, a recalibration is necessary whenever the process or the setup changes even slightly. With a large and diverse Raman dataset, however, it was possible to generate generic partial least squares regression models to reliably predict the concentrations of important metabolic compounds, such as glucose-, lactate-, and glutamine-indifferent CHO cell cultivations. The data for calibration were collected from various cell cultures from different sites in different companies using different Raman spectrophotometers. In testing, the developed “generic” models were capable of predicting the concentrations of said compounds from a dilution series in FMX-8 mod medium, as well as from an independent CHO cell culture. These spectra were taken with a completely different setup and with different Raman spectrometers, demonstrating the model flexibility. The prediction errors for the tests were mostly in an acceptable range (<10% relative error). This demonstrates that, under the right circumstances and by choosing the calibration data carefully, it is possible to create generic and reliable chemometric models that are transferrable from one process to another without recalibration.
Online monitoring of sourdough fermentation using a gas sensor array with multivariate data analysis
(2023) Anker, Marvin; Yousefi-Darani, Abdolrahim; Zettel, Viktoria; Paquet-Durand, Olivier; Hitzmann, Bernd; Krupitzer, Christian
Sourdough can improve bakery products’ shelf life, sensory properties, and nutrient composition. To ensure high-quality sourdough, the fermentation has to be monitored. The characteristic process variables for sourdough fermentation are pH and the degree of acidity measured as total titratable acidity (TTA). The time- and cost-intensive offline measurement of process variables can be improved by utilizing online gas measurements in prediction models. Therefore, a gas sensor array (GSA) system was used to monitor the fermentation process of sourdough online by correlation of exhaust gas data with offline measurement values of the process variables. Three methods were tested to utilize the extracted features from GSA to create the models. The most robust prediction models were achieved using a PCA (Principal Component Analysis) on all features and combined two fermentations. The calibrations with the extracted features had a percentage root mean square error (RMSE) from 1.4% to 12% for the pH and from 2.7% to 9.3% for the TTA. The coefficient of determination (R2) for these calibrations was 0.94 to 0.998 for the pH and 0.947 to 0.994 for the TTA. The obtained results indicate that the online measurement of exhaust gas from sourdough fermentations with gas sensor arrays can be a cheap and efficient application to predict pH and TTA.