Seite - 134 - in Adaptive and Intelligent Temperature Control of Microwave Heating Systems with Multiple Sources
Bild der Seite - 134 -
Text der Seite - 134 -
5. ExperimentalResults
whenever it isswitchedon, thefrequencyandphaseof theoutputmi-
crowave is not fixed. If there is no stable heating pattern from each
source, the whole microwave heating system will become a highly
stochastic system where the future temperature is not predictable by
neitherof the twomodels.
If a stable heating pattern from each source can be guaranteed, the
second part is to see if the combinations of any two or more feed-
ing sources can provide stable heating patterns. This is important for
the modeling. Because in practice when multiple feeding sources are
switched on at the same time, unexpected coupling effects will occur
between different sources. It is possible that when multiple sources
areswitchedonsimultaneously, theresultingsuperposedheatingpat-
terns differ a lot from time to time, which could also make the system
identification process more difficult and the models unreliable. After
the first two aspects are confirmed, the last part of the validation is to
verify that if the scalar and the vector addition principles are able to
describe thepowersuperpositionscorrectly.
The setup used in the validations is shown as in figure 5.1. The tem-
peraturedistributionof this setupwasmonitoredbyaninfraredcam-
era in real time. All following experiments were done at the same
temperature range (30◦C∼ 32◦C) and the temperature of surround-
ing air was also the same (19◦C∼ 21◦C), therefore all temperature-
dependentparameterscanbeconsideredasconstants.
(a) y
x.z
Sealant
Vacuum
Bagging Film
Thermo-electrical
Foil
Vacuum Hose
Silicone Rubber
Foil
Aluminum
Plate
(b)
Figure5.1. Thesetupusedinverificationexperiments.
134
Adaptive and Intelligent Temperature Control of Microwave Heating Systems with Multiple Sources
- Titel
- Adaptive and Intelligent Temperature Control of Microwave Heating Systems with Multiple Sources
- Autor
- Yiming Sun
- Verlag
- KIT Scientific Publishing
- Ort
- Karlsruhe
- Datum
- 2016
- Sprache
- englisch
- Lizenz
- CC BY-SA 3.0
- ISBN
- 978-3-7315-0467-2
- Abmessungen
- 14.8 x 21.0 cm
- Seiten
- 260
- Schlagwörter
- Mikrowellenerwärmung, Mehrgrößenregelung, Modellprädiktive Regelung, Künstliches neuronales Netz, Bestärkendes Lernenmicrowave heating, multiple-input multiple-output (MIMO), model predictive control (MPC), neural network, reinforcement learning
- Kategorie
- Technik