Search

Bioindicative methods involving the identification and counting of indicator organisms (e.g. algae) are widely used methods in the assessment of surface water quality. For this reason, the purpose of this paper was automatic image analysis using the YOLO v8 deep learning neural network, directed at the detection of freshwater algae Cyclotella. Changes in the number of these organisms can indicate changes in the water quality and the trophic status of the reservoir, which makes automating their detection an important task. Traditionally, the detection and counting of objects in microscope images was done manually, but by using machine learning and especially neural networks, the process can be automated. YOLO (You Only Look Once) is an example of a network that, after proper training and validation, is capable of performing image detection in real time. In this study, the Roboflow object tagging tool was used to create a dataset divided into training, validation and test sets. Training of the network, validation of the model and evaluation of its metrics were carried out. The paper presents the obtained metrics of the YOLO v8 network on the validation set, such as Accuracy = 0.960, Precision = 0.964, Recall = 0.995. The presented results confirm the effectiveness of the applied method in automatic analysis of microscopic images containing algae and thus the high application potential of the method in supporting bioindication studies of surface water quality. [ABSTRACT FROM AUTHOR]

Among the many methods of joining different materials, gluing is characterized by its most specific nature. In comparison with, for example, welded, screwed, or overlapped connections, a glued connection depends on the largest number of factors. Many of them are related to the phenomenon of adhesion, which is complicated by definition. It has many shapes and forms, and its existence determines not only the durability of such a joint but also the possibility of its execution. Epoxy polymers are among the most commonly used adhesives. Their extremely good parameters can be easily modified by additives in the form of fillers. Compatibility between the filler and the adhesive allows for further improving the adhesive parameters in the glued joint. However, in order to effectively combine the adhesive and the filler, different, often specific mixing methods must be used. The following study presents the results obtained in an experimental research program, the aim of which was to increase the adhesion of epoxy resin to a properly prepared concrete substrate. As a method to increase the final adhesion, the addition of microsilica and carbon nanotubes in an experimentally determined amount was selected. The use of sonication as a mixing method together with cavitation allowed for improving the parameters which determine the final adhesion of the adhesive to concrete. The parameters which were selected to describe the course of changes in the adhesion of the adhesive to the concrete substrate were the viscosity, free surface energy, surface parameters, adhesion, and SEM images of the tested resin in various modification configurations. The obtained results make it possible to form stronger and more durable adhesive joints during the reinforcement of concrete structural elements using fiber-reinforced polymer (FRP) composites. [ABSTRACT FROM AUTHOR]

The article contains the procedure of image acquisition, including sampling of analyzed material as well as technical solutions of hardware and preprocessing used in research. A dataset of digital images containing identified objects were obtained with help of automated mechanical system for controlling the microscope table and used to train the YOLO models. The performance of YOLOv4 as well as YOLOv8 deep learning networks was compared on the basis of automatic image analysis. YOLO constitutes a one-stage object detection model, aiming to examine the analyzed image only once. By utilizing a single neural network, the image is divided into a grid of cells, and predictions are made for bounding boxes, as well as object class probabilities for each box. This approach allows real-time detection with minimal accuracy loss. The study involved ciliated protozoa Vorticella as a test object. These organisms are found both in natural water bodies and in treatment plants that employ the activated sludge method. As a result of its distinct appearance, high abundance and sedentary lifestyle, Vorticella are good subjects for detection tasks. To ensure that the training dataset is accurate, the images were manually labeled. The performance of the models was evaluated using such metrics as accuracy, precision, and recall. The final results show the differences in metrics characterizing the obtained outputs and progress in the software over subsequent versions of the YOLO algorithm. [ABSTRACT FROM AUTHOR]

An extensive methodology for analyzing the impact of catchment and sewer network retention on drainage system operating conditions during hydraulic overloading is presented. To evaluate the performance of the sewer system and identify the need for repair actions, logistic regression models were developed to predict the unit flooding volume and manhole overflowing. An advanced sensitivity analysis was performed to determine the key parameters (retention and roughness of impervious and pervious areas as well as sewer channel retention) conditioning the reduction of uncertainty in the simulation results and ensuring the assumed hydraulic effect. A coefficient expressing the quotient of the duration of rainfall conditioning the exceedance of the limits of the unit flooding volume (13 m³·ha−1) as well as the degree of overflowed manholes (0.32) was determined, allowing the determination of the key performance criterion of the sewer network to take corrective action depending on field and channel retention. It was shown that the catchment area retention had the key influence on the conditions of sewer operation and the probability of remedial work. Increasing the rainfall duration led to a decrease in sensitivity coefficients with respect to the identified parameters of the SWMM model, which is important when selecting rainfall events for the calibration and validation sets. The usefulness of the developed methodology was demonstrated at the stage of building mechanistic models, which is of significance when planning field studies. [ABSTRACT FROM AUTHOR]

In this article, the results of studies testing the anisotropy of autoclaved aerated concrete in terms of water and heat transport are presented. Using image analysis techniques, a study was conducted on four different samples of concrete produced in the same process. To ensure the comparability of results, the pictures were taken from a fixed distance with the same lens settings trimmed to a set size. Cross-sectional profiles of the material were examined and were arranged in two directions: perpendicular and parallel to the growth direction occurring in the autoclave. For each block, approximately 4750 objects were obtained, with an average of 2700 objects along the wall and 2050 across it. As a result of the comparative analysis, metrics concerning pores, significantly distinguishing the profile direction, were identified. These included the pore area (area), the maximum and minimum distance between points on the perimeter (Feret, MinFeret), lengths of the major and minor axes of the fitted ellipse (major, minor), and the ratio of the area of selection to its convex hull (solidity). As a reference, standard investigations were conducted for moisture transport using the time domain reflectometry setup and for thermal conductivity values using the steady-state heat flow plate apparatus. [ABSTRACT FROM AUTHOR]

The examinations of concrete involved partial substitution of cement with cement kiln dust (CKD) 0, 5, 10, 20 and 30%. The water/cement (w/c) ratio amounted to 0.36. The obtained findings pertaining to open porosity, density, and volumetric density were found to correlate with the capillary action and absorptivity of the analyzed types of concrete. With the maximum addition of CKD, i.e. 30%, open porosity decreased by 35%. In turn, CKD added in the amount of 5% resulted in a slightly reduced addition compressive strength, amounting to 1.3% and 2.1% following 28 days and 56 days of concrete curing, respectively. After 28 days, the differences in strength were greater when the additive was supplied in higher amounts, i.e. 10%, 20%, and 30%, resulting in 6.5%, 13.4%, and 22.9% decrease, respectively, in spite of strength improvement. In terms of flexural and splitting tensile strengths, comparable relations were noted. As far as the frost resistance test results are concerned, the mass losses in all examined concretes were not significant, reaching up to 0.5%. The strength reduction in the case of the first three series of concretes was below 3%. When the CKD addition was increased to 20% and 30%, the value of the dynamic modulus of elasticity Ec,s decreased to a greater degree, by 8.0% and 14.7%, respectively. The hydrophobization effect is best seen in CKD-free concrete. After the impregnation, the loss of mass following the frost test of the samples is reduced by half. With a higher CKD content, the hydrophobization effectiveness is insignificant. The most favourable results were observed for hydrophobization with the oligomer-based preparation A1. [ABSTRACT FROM AUTHOR]

The representation of Peritricha ciliates was studied in the activated sludge of two wastewater treatment plants (WWTP), one of which operates using a technology that includes alternating aerobic, anoxic and anaerobic conditions in bioreactors (Lublin, Poland), and the other - only aerobic conditions (Sumy, Ukraine). During the study, 14 Peritricha species were identified in the WWTP Lublin, and 13 species were identified in the WWTP Sumy. The similarity of species lists was 81.5% (Sørensen index). On the basis of on the similarity and taking into account the occurrence rate (= 60%), a common group of Peritricha species characteristic of the activated sludge from these two types of treatment facilities was identified, which includes 4 species of colonial Peritricha: Carchesium polypinum, Epistylis coronata, Epistylis longicaudatum and Opercularia articulata, and also 4 species of solitary Peritricha: Vorticella aquadulcis, Vorticella convallaria, Vorticella infusionum and Vorticella microstoma. Despite the very high similarity in species composition, statistical analysis of the population structure of Peritricha showed a clear separation of two WWTPs with different wastewater treatment technologies. If there is a significant similarity in the species composition of Peritricha, the species, based on their abundance and occurrence, are divided into two groups, focused on different technological schemes. The population structure of Peritricha responds to the changes in purification technology, showing the changes not so much in species composition as in their quantitative structure. The differences in bioreactor conditions and increased effluent treatment efficiency demonstrated by the WWTP Lublin result in differences in Peritricha species structure, which are reflected in higher Peritricha abundance in WWTP Lublin compared to WWTP Sumy. [ABSTRACT FROM AUTHOR]

In line with the European Parliament's Resolution of February 10th, 2021 on the new action plan for a closed economy, most of the activities undertaken in the wastewater treatment process should focus on the search for new technologies that use wastewater as a source of water and nutrients. The paper reviews the concept of water reuse in industrial installations, with special emphasis on the use of membrane technologies for this purpose. The results of authors' own research on effectiveness of using ultrafiltration (UF) and reverse osmosis (RO) processes to recover process water from brewery wastewater, following pretreatment by the BIOPAQ®-IC process, are presented. Raw wastewater, after averaging the parameters, was digested in an anaerobic reactor, followed by deodorization and oxidation of sulfides to sulfate in an oxidation process in a pretreatment tank. The water recovered from pretreated brewery wastewater by UF and RO membrane techniques was found to be suitable for boiler feed, cooling technology and washing process without directly cleaning beer bottles. The study used a ZeeWeed capillary immersion ultrafiltration module operating under vacuum and a module equipped with a Filmtec XLE 2125 reverse osmosis membrane. The technology improved the efficiency of contaminant removal, yielding purified and high-quality water toward the implementation of the assumptions of Circular Economy and Green Deal Implementation. [ABSTRACT FROM AUTHOR]