Institutional Repository of Vilnius University
Automatinis temperatūros valdymas naudojant dirbtinį neuroninį tinklą mikrovaldiklyje /
Abstract
dc:descriptionThe aim of this work is to develop an automatic temperature controller based on artificial neural networks improved proportional-integral-differential PID control algorithm. The suitability of this control algorithm for temperature control is investigated. Based on the acquired programming knowledge, a three-layer artificial neural network is created, the inner layer of which is represented by proportional, integral and differential components, respectively. A controller is designed and developed using an Arduino Uno microcontroller, a transistor and a temperature sensor. Based on the set value, the Arduino Uno controller sends a pulse width modulation signal to regulate the temperature of the heating element of the 3D printer. The transistor amplifies the control signal from five to twelve volts. Using the MATLAB application programming interface, a comparison of PID control algorithms used in practice and the developed PID artificial neural network is performed. The PID artificial neural network control algorithm implemented in the physical controller is able to properly control the temperature of the heating element not worse than the PID used in practice, but control accuracy is limited by the physical properties of the controller.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Maniušis, Justinas,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD192846944&prefLang=en_US