Iskanje po katalogu digitalne knjižnice

Opis: Corn drying is a critical post-harvest process to ensure product quality and compliance with moisture standards. Traditional optimization approaches often overlook dynamic interactions between operational parameters and environmental factors in industrial continuous flow drying systems. This study integrates statistical analysis and deep learning to predict outlet moisture content, leveraging a dataset of 3826 observations from an operational dryer. The effects of inlet moisture, target air temperature, and material discharge interval on thermal behavior of the system were evaluated through linear regression and t-test, which provided interpretable insights into process dependencies. Three neural network architectures (LSTM, GRU, and TCN) were benchmarked for multivariate time-series forecasting of outlet corn moisture, with hyperparameters optimized using grid search to ensure fair performance comparison. Results demonstrated GRU’s superior performance in the context of absolute deviations, achieving the lowest mean absolute error (MAE = 0.304%) and competitive mean squared error (MSE = 0.304%), compared to LSTM (MAE = 0.368%, MSE = 0.291%) and TCN (MAE = 0.397%, MSE = 0.315%). While GRU excelled in average prediction accuracy, LSTM’s lower MSE highlighted its robustness against extreme deviations. The hybrid methodology bridges statistical insights for interpretability with deep learning’s dynamic predictive capabilities, offering a scalable framework for real-time process optimization. By combining traditional analytical methods (e.g., regression and t-test) with deep learning-driven forecasting, this work advances intelligent monitoring and control of industrial drying systems, enhancing process stability, ensuring compliance with moisture standards, and indirectly supporting energy efficiency by reducing over drying and enabling more consistent operation.
Ključne besede: advanced drying technologies, continuous flow drying, time-series forecasting, LSTM, GRU, TCN, deep learning, statistical analysis, optimization of the drying process
Objavljeno v DKUM: 03.11.2025; Ogledov: 0; Prenosov: 3
Celotno besedilo (3,02 MB)
Gradivo ima več datotek! Več...

Opis: As we move toward Agriculture 4.0, there is increasing attention and pressure on the productivity of food production and processing. Optimizing efficiency in critical food processes such as corn drying is essential for long-term storage and economic viability. By using innovative technologies such as machine learning, neural networks, and LSTM modeling, a predictive model was implemented for past data that include various drying parameters and weather conditions. As the data collection of 3826 samples was not originally intended as a dataset for predictive models, various imputation techniques were used to ensure integrity. The model was implemented on the imputed data using a multilayer neural network consisting of an LSTM layer and three dense layers. Its performance was evaluated using four objective metrics and achieved an RMSE of 0.645, an MSE of 0.416, an MAE of 0.352, and a MAPE of 2.555, demonstrating high predictive accuracy. Based on the results and visualization, it was concluded that the proposed model could be a useful tool for predicting the moisture content at the outlets of continuous drying systems. The research results contribute to the further development of sustainable continuous drying techniques and demonstrate the potential of a data-driven approach to improve process efficiency. This method focuses on reducing energy consumption, improving product quality, and increasing the economic profitability of food processing
Ključne besede: drying, moisture prediction, big data, artificial intelligence, LSTM
Objavljeno v DKUM: 21.03.2025; Ogledov: 0; Prenosov: 13
Celotno besedilo (2,99 MB)
Gradivo ima več datotek! Več...

Opis: 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.
Ključne besede: sušilni sistem, globoko učenje, LSTM, napovedovanje, optimizacija, koruza, vlaga
Objavljeno v DKUM: 28.03.2024; Ogledov: 275; Prenosov: 113
Celotno besedilo (3,60 MB)

Opis: V diplomski nalogi se ukvarjamo z napovedovanjem porabe pitne vode. Naš glavni cilj je primerjava napovednih modelov SARIMA in nevronske mreže LSTM. Pri napovedovanju se osredotočimo na časovne vrste posameznih gospodinjstev ter časovne vrste vodovodnega omrežja, ki so vzorčene mesečno. Primerjavo napovednih modelov izvedemo na podlagi njihove srednje kvadratne napake pri prileganju na časovno vrsto in napovedovanju porabe pitne vode na testni množici. Rezultati pokažejo, da se najbolje obnese model ARIMA.
Ključne besede: časovne vrste, napovedovanje, ARIMA, LSTM
Objavljeno v DKUM: 13.02.2023; Ogledov: 2260; Prenosov: 127
Celotno besedilo (1,83 MB)

Opis: Namen diplomskega dela je bil razviti pametno vremensko postajo s spletno aplikacijo, ki bi omogočala napoved temperature do pet dni vnaprej. Želeli smo tudi preizkusiti kako natančne so napovedi z različnimi modeli in metodami. V diplomskem delu predstavimo zasnovo in implementacijo rešitve. Na koncu podamo rezultate napovedi. Celoten sistem je sestavljen iz razvojne plošče platforme Arduino, senzorja temperature in vlage, oblačne podatkovne baze in računalniškega strežnika z integracijo napovednih metod, ki omogoča uporabniku dostop do spletne aplikacije z vsemi rezultati v domačem omrežju.
Ključne besede: napoved temperature, Arduino, LSTM, SARIMA
Objavljeno v DKUM: 18.10.2021; Ogledov: 1002; Prenosov: 130
Celotno besedilo (1,67 MB)