RESUMEN
Soft sensors based on deep learning regression models are promising approaches to predict real-time fermentation process quality measurements. However, experimental datasets are generally sparse and may contain outliers or corrupted data. This leads to insufficient model prediction performance. Therefore, datasets with a fully distributed solution space are required that enable effective exploration during model training. In this study, the robustness and predictive capability of the underlying model of a soft sensor was improved by generating synthetic datasets for training. The monitoring of intensified ethanol fermentation is used as a case study. Variational autoencoders were employed to create synthetic datasets, which were then combined with original datasets (experimental) to train neural network regression models. These models were tested on original versus augmented datasets to assess prediction improvements. Using the augmented datasets, the soft sensor predictive capability improved by 34%, and variability was reduced by 82%, based on R2 scores. The proposed method offers significant time and cost savings for dataset generation for the deep learning modeling of ethanol fermentation and can be easily adapted to other fermentation processes. This work contributes to the advancement of soft sensor technology, providing practical solutions for enhancing reliability and robustness in large-scale production.
RESUMEN
Phenolic compounds such as vanillic and p-coumaric acids are pollutants of major concern in the agro-industrial processing, thereby their effective detection in the industrial environment is essential to reduce exposure. Herein, we present the quenching effect of these compounds on the electrochemiluminescence (ECL) of the Ru(bpy)32+ /TPrA (TPrA=tri-n-propylamine) system at a disposable screen-printed carbon electrode. Transient ECL profiles are obtained from multiple video frames following 1.2â V application by a smartphone-based ECL sensor. A wide range of detection was achieved using the sensor with limit of detection of 0.26â µM and 0.68â µM for vanillic and p-coumaric acids, respectively. The estimated quenching constants determined that the quenching efficiency of vanillic acid is at least two-fold that of p-coumaric acid under the current detection conditions. The present ECL quenching approach provided an effective method to detect phenolic compounds using a low-cost, portable smartphone-based ECL sensor.