magistrsko delo
Marko Simonič (Author), Simon Klančnik (Mentor), Blaž Frešer (Mentor), Jernej Hernavs (Co-mentor)

Abstract

Magistrsko delo obsega opis razvoja in implementacije modela globoke nevronske mreže z LSTM arhitekturo. Model omogoča napovedovanje vlažnosti koruze na izhodu iz sušilnega sistema na podlagi meritev vlažnosti koruze na vhodu in beleženja temperaturnih parametrov med obratovanjem. Razvoj modela je vključeval temeljito analizo in preučitev posameznih temperaturnih parametrov. Pri tem smo izvedli regresijsko analizo, ki je raziskovala vpliv vhodne vlažnosti, ciljne temperature gorilnika in časa sušenja med izpusti koruze na spremembe temperaturnih parametrov v sušilnem sistemu. Poleg tega smo preučili tudi statistične vplive samih temperaturnih parametrov na vlažnost koruze na izhodu iz sušilnega sistema. Analiza nam je omogočila ustrezno pripravo podatkov za učenje napovednih modelov. Uspešnost razvitih napovednih modelov je ocenjena s povprečno absolutno napako (angl. mean absolute error – MAE), povprečno kvadratno napako (angl. mean squared error – MSE), korenom povprečne kvadratne napake (angl. root mean squared error – RMSE) in srednjo absolutno odstotkovno napako (angl. mean absolute percentage error – MAPE). Najuspešnejši model za napovedovanje vlažnosti na izhodu iz sušilnega sistema je imel na učnih podatkih odlično zmogljivost napovedovanja, saj so povprečne vrednosti MAE znašale 0,352, RMSE 0,645, MSE 0,416 in MAPE 2,555. Izvedena je bila tudi vizualizacija rezultatov za nadaljnjo analizo in interpretacijo.

Keywords

sušilni sistem;globoko učenje;LSTM;napovedovanje;optimizacija;koruza;vlaga;magistrske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UM FS - Faculty of Mechanical Engineering
Publisher: [M. Simonič]
UDC: [004.8+519.2]:66.047.4/.6(043.2)
COBISS: 191934979 Link will open in a new window
Views: 59
Downloads: 12
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Analysis and optimization of process parameters in corn drying system
Secondary abstract: The master's thesis encompasses the description of the development and implementation of a deep neural network model with LSTM architecture. The model enables the prediction of corn moisture content at the output of the drying system based on input moisture measurements and logging of temperature parameters during operation. The development of the model involved a thorough analysis and examination of individual temperature parameters, including conducting regression analysis to explore the influence of input moisture, target burner temperature, and pause time between corn discharges on changes in temperature parameters in the drying system. Additionally, we examined the statistical effects of the temperature parameters themselves on the output moisture content of corn. The analysis allowed us to properly prepare the data for training the predictive model. The performance of developed predictive models is evaluated using mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE) and mean absolute percentage error (MAPE). The most successful model for predicting moisture at the output of the drying system exhibited excellent predictive performance on the training data, with average MAE values of 0.352, RMSE of 0.645, MSE of 0.416, and MAPE of 2.555. Visualization of the results was also conducted for further analysis and interpretation.
Secondary keywords: drying system;deep learning;LSTM;forecast;optimization;corn;moisture;
Type (COBISS): Master's thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za strojništvo, GING
Pages: 1 spletni vir (1 datoteka PDF (XII, 99 f. ))
ID: 23122954