| Autor: |
Konrad Grzeszczyk, Markiyan Nakonechnyi, Stanislav Novosad, Orest Ivakhiv, Volodymyr Kochan, Orest Kochan, Volodymyr Vyshnia, Anatoliy Sachenko, Lukasz Kopania, Oleksandr Osolinskyi |
| Rok vydání: |
2020 |
| Předmět: |
|
| Zdroj: |
2020 IEEE 2nd International Conference on System Analysis & Intelligent Computing (SAIC). |
| DOI: |
10.1109/saic51296.2020.9239224 |
| Popis: |
Authors have developed a method of control over one of the main technological processes of manufacturing foil solar panels, i.e., burning tracks in the layers of semiconductor material and insulation. The proposed method is based on neural networks trained directly on the control object. This eliminates the laborious process of identifying the parameters of the control object mathematical model and the impact of its error on the training outcomes. To clarify the conditions for optimizing a certain law for generating the control action by neural networks various laws of control have been simulated. It’s established that laws of control can be changed according to the current situation of the control object. Simulation outcomes proofed that the most efficient is the system with the PI- controller. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
