Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: PM pollution

Sortuj według:

Ogranicz wyniki do:

Computational fluid dynamics (CFD) aided design of a multi-rotor flying robot for locating sources of particulate matter pollution

Suchanek Grzegorz, Filipek Roman

Applied Computer Science

2022

Vol. 18, no 3

86--104

The use of flying robots for various environmental protection issues is a very important and current research topic. Designing a dedicated multi-rotor flying robot is necessary for the efficient and automated localization of sources of air pollution, especially solid particles. In particular, one of the most important requirements that must be met by such a robot is its appropriate impact on the measurement process, i.e., increasing the sensitivity of sensors or reducing the interference. This is particularly difficult because its rotating rotors introduce significant disturbances to the surrounding fluid. In these studies, the design process is supported by the creation of a mathematical flow model and a series of analyzes to optimize the PM measurement system. The model is built using the finite-volume method in ANSYS Fluent software and steady-state RANS averaging. First, a flow field model with one propeller was modeled and its parameters identified by comparison with the results from the dedicated original dynamometer stand -- characteristics of the propeller performance. On the basis of the simulations and measurement of one rotor, subsequent systems of the highest practical importance are built. The effect of that design process was the preparation and testing of a functional robot prototype. The field parameter distributions resulting from the analyzes, in particular the turbulence intensity, allow one to propose a criterion on the basis of which both the best rotor configuration and localization of sensors are selected.

Bagging and boosting techniques in prediction of particulate matters

Triana D., Osowski S.

Bulletin of the Polish Academy of Sciences. Technical Sciences

2020

Vol. 68, nr 5

1207--1215

The paper presents new ensemble solutions, which can forecast the average level of particulate matters PM10 and PM2.5 with increased accuracy. The proposed network is composed of weak predictors integrated into a final expert system. The members of the ensemble are built based on deep multilayer perceptron and decision tree and use bagging and boosting principle in elaborating common decisions. The numerical experiments have been carried out for prediction of daily average pollution of PM10 and PM2.5 for the next day. The results of experiments have shown, that bagging and boosting ensembles employing these weak predictors improve greatly the quality of results. The mean absolute errors have been reduced by more than 30% in the case of PM10 and 20% in the case of PM2.5 in comparison to individually acting predictors.