Wyniki wyszukiwania - BazTech

1

Environmental analysis of a product manufactured with the use of an additive technology – AI-based vs. traditional approaches

Dostatni Ewa, Dudkowiak Anna, Rojek Izabela, Mikołajewski Dariusz

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2023

|

Vol. 71, nr 1

art. no. e144478

EN

This paper attempts to conduct a comparative life cycle environmental analysis of alternative versions of a product that was manufactured with the use of additive technologies. The aim of the paper was to compare the environmental assessment of an additive-manufactured product using two approaches: a traditional one, based on the use of SimaPro software, and the authors’ own concept of a newly developed artificial intelligence (AI) based approach. The structure of the product was identical and the research experiments consisted in changing the materials used in additive manufacturing (from polylactic acid (PLA) to acrylonitrile butadiene styrene (ABS)). The effects of these changes on the environmental factors were observed and a direct comparison of the effects in the different factors was made. SimaPro software with implemented databases was used for the analysis. Missing information on the environmental impact of additive manufacturing of PLA and ABS parts was taken from the literature for the purpose of the study. The novelty of the work lies in the results of a developing concurrent approach based on AI. The results showed that the artificial intelligence approach can be an effective way to analyze life cycle assessment (LCA) even in such complex cases as a 3D printed medical exoskeleton. This approach, which is becoming increasingly useful as the complexity of manufactured products increases, will be developed in future studies.

2

Incidences of variables in labor absenteeism: an analysis of neural networks

Pérez-Campdesuñer Reyner, De Miguel-Guzmán Margarita, García-Vidal Gelmar, Sánchez-Rodríguez Alexander, Martínez-Vivar Rodobaldo

Management and Production Engineering Review

|

2020

|

Vol. 11, No. 1

3–-12

EN

Labor absenteeism is a factor that affects the good performance of organizations in any part of the world, from the instability that is generated in the functioning of the system. This is evident in the effects on quality, productivity, reaction time, among other aspects. The direct causes by which it occurs are generally known and with greater reinforcement the diseases are located, without distinguishing possible classifications. However, behind these or other causes can be found other possible factors of incidence, such as age or sex. This research seeks to explore, through the application of neural networks, the possible relationship between different variables and their incidence in the levels of absenteeism. To this end, a neural networks model is constructed from the use of a population of more than 12,000 employees, representative of various classification categories. The study allowed the characterization of the influence of the different variables studied, supported in addition to the performance of an ANOVA analysis that allowed to corroborate and clarify the results of the neural network analysis.

3

Analiza jakościowa modeli neuronowych na przykładzie wytrzymałości kinetycznej granul

Rynkiewicz M.

Inżynieria Rolnicza

|

2006

|

R. 10, nr 6(81)

241-248

PL

W pracy dokonano analizy działania modeli neuronowych, które różniły się parametrami tj. liczbą neuronów i liczbą warstw ukrytych. Ocenę jakości działania przeprowadzono w oparciu o wartości uzyskanych błędów względnych i odchylenia standardowego. Do nauczania sieci neuronowych wykorzystano dane, dotyczące zależności pomiędzy średnią średnicą granulowanych cząstek komponentów i temperatury pary wodnej podawanej do kondycjonera granulatora a wytrzymałością kinetyczną granul.

EN

In this work analyses of action of neural model were made. The neural models differed in parameters: number of neurons and the number of hidden layers. The assessment of the quality of action was carried in the support of relative mistakes gotten about value and of standard deviation. Data, concerning the relation was used to teaching neural networks between the average diameter particles of components and the temperature of given steam to conditioner and with kinetic durability of pellets.

4

Zastosowanie sztucznych sieci neuronowych do modelowania stężenia ozonu przy powierzchni ziemi

Baran J., Świąć A., Hoffman S.

Inżynieria i Ochrona Środowiska

|

1999

|

T. 2, nr 3/4

305-321

PL

Zbadano możliwości zastosowania sieci neuronowych do modelowania stężenia ozonu przy powierzchni ziemi. Analizę przeprowadzono na podstawie zbioru danych pomiarowych, dla którego we wcześniejszych pracach uzyskano metodami statystycznymi liniowy model regresji wielowymiarowej, uzależniający stężenie ozonu od temperatury, prędkości wiatru i stężenia tlenków azotu NOx. W obliczeniach wykorzystano dane zarejestrowane w 1994 r. na stacji pomiarowej monitoringu powietrza w Krakowie przy ulicy Halickiej. Analizowany zbiór danych stanowiły zmierzone w godzinach nocnych wartości stężeń O3, NOx, temperatury i prędkości wiatru uśrednione w okresach 60-minutowych. Jakość kilku modeli otrzymanych z użyciem sieci neuronowych porównano ze sobą oraz z modelem liniowej regresji wielowymiarowej. Przyjęto dwa kryteria oceny modeli: 1) wartość błędu średniokwadratowego wynikającego z rozbieżności między wyjściem modelu a wartościami rzeczywistymi stężenia O3; 2) wartość współczynnika korelacji dla prostej regresji pomiędzy wyjściem modelu (przewidywaniami) a wartościami rzeczywistymi stężenia O3. Stwierdzono, że modele neuronowe są zdecydowanie lepsze od liniowego. Zweryfikowano pozytywnie zdolność modeli neuronowych do przewidywania wyników dla danych niewykorzystywanych w procesie uczenia, czyli możliwość uogólniania zdobytej wiedzy.

EN

Possibility of neural networks application to the ozone concentration modelling near the ground was examined. The studies were performed based on the measuring data set that was earlier used for generation of multiple linear regression model, conditioning ozone concentration by temperature, wind speed and NOx, concentration. The data gathered in 1994 at the air monitoring station in Cracow were used in the calculations. The analysed data set was built of 60-minutes' averages of temperature, wind speed as well as O3 and NOX concentrations, measured at night. Qualities of some models obtained with neural networks were co m pa red with the multiple linear regression model. Two criteria of model estimation were assumed: 1) the value of mean square error resulting from divergences between model input and real O3 concentration values; 2) the value of correlation coefficient for the best linear fit of the real O3 concentration values to the model input. It was stated that the neural networks models are decidedly better than the linear regression model. Ability of neural models to predict results for the data not used in training process was affirmatively verified.