RESUMEN

Investigating the interaction between influent particles and biomass is basic and important for the biological wastewater treatment. The micro-level methods allow for this, such as the microscope image analysis method with the conventional ImageJ processing software. However, these methods are cost and time-consuming, and require a large amount of work on manual parameter tuning. To deal with this problem, we proposed a deep learning (DL) method to automatically detect and quantify microparticles free from biomass and entrapped in biomass from microscope images. Firstly, we introduced a "TU Delft-Interaction between Particles and Biomass" dataset containing labeled microscope images. Then, we built DL models using this dataset with seven state-of-the-art model architectures for a instance segmentation task, such as Mask R-CNN, Cascade Mask R-CNN, Yolact and YOLOv8. The results show that the Cascade Mask R-CNN with ResNet50 backbone achieves promising detection accuracy, with a mAP50box and mAP50mask of 90.6 % on the test set. Then, we benchmarked our results against the conventional ImageJ processing method. The results show that the DL method significantly outperforms the ImageJ processing method in terms of detection accuracy and processing cost. The DL method shows a 13.8 % improvement in micro-average precision, and a 21.7 % improvement in micro-average recall, compared to the ImageJ method. Moreover, the DL method can process 70 images within 1 min, while the ImageJ method costs at least 6 h. The promising performance of our method allows it to offer a potential alternative to examine the interaction between microparticles and biomass in biological wastewater treatment process in an affordable manner. This approach offers more useful insights into the treatment process, enabling further reveal the microparticles transfer in biological treatment systems.

Asunto(s)

RESUMEN

This study reports the effects of microaeration on a laboratory-scale AnMBR (MA-AnMBR) fed with synthetic concentrated domestic sewage. The imposed oxygen load mimics the oxygen load coming from a dissolved air flotation (DAF) unit, establishing an anaerobic digester-DAF (AD-DAF) combination with sludge recycling. Results showed a reduced COD concentration in the MA-AnMBR permeate compared with the AnMBR permeate, from 90 to 74 mgCOD L-1, and a concomitant 27% decrease in biogas production. The MA-AnMBR permeate ammonium (NH4+) concentration increased by 35%, to 740 mgNH4+-N L-1, indicating a rise in the hydrolytic capacity. Furthermore, the MA-AnMBR biomass seemingly adapted to an increased oxygen load, which corresponded to 1% of the influent COD load (approximately 55 mLO2 d-1). Concomitantly, an increase in the superoxide dismutase activity (SOD) of biomass was detected. Meanwhile, negligible changes were observed in the specific methanogenic activity (SMA) of the microaerated biomass that was subjected to an oxygen load equivalent to 3% of the influent COD load in batch tests. The obtained results showed that an AD-DAF system could be a promising technology for treating concentrated domestic wastewater, improving sewage sludge hydrolysis, and overall organic matter removal when compared to an AnMBR.