Browsing 2024 International Conference "Electrical, Electronic and Information Sciences“ (eStream) by Department "Mechanikos mokslo institutas / Institute of Mechanical Science"
Now showing items 1-4 of 4
-
An Experimental Selection of Deep Neural Network Hyperparameters for Engine Emission Prognosis
(2024 IEEE Open Conference of Electrical, Electronic and Information Sciences (eStream), April 25, 2024, Vilnius, Lithuania, 2024)This research presents results and discussion on prognostic deep learning models developed for the prediction of emission parameters of internal combustion engines. The resulting models were trained to predict various ... -
Investigation of Accuracy of Linear Motor Positioning Systems using Different Filters
(2024 IEEE Open Conference of Electrical, Electronic and Information Sciences (eStream), April 25, 2024, Vilnius, Lithuania, 2024)Fast-paced competition in the industrial environment requires high-precision, high-performance systems that allow industry players to stay on top. Precise changes to the mechanical structure of the positioning system are ... -
The Study of the Dynamics Limits of Gas Flow in the Connecting Channels of Agglomeration Apparatus
(2024 IEEE Open Conference of Electrical, Electronic and Information Sciences (eStream), April 25, 2024, Vilnius, Lithuania, 2024)Ambient air quality is considered one of the indicators of a sustainable lifestyle. Traditional cleaning technologies based on gravitational, centrifugal, electrostatic, and other operating principles are not effective in ... -
Time Series Data Augmentation Methods for Deep Learning Models in Conveyor Belt Load Classification
(2024 IEEE Open Conference of Electrical, Electronic and Information Sciences (eStream), April 25, 2024, Vilnius, Lithuania, 2024)This work explores time series data augmentation methods for deep learning and their application for conveyor belt tension signals. In this research, conveyor belt load data was collected and analyzed for five different ...