Seite - 139 - in Adaptive and Intelligent Temperature Control of Microwave Heating Systems with Multiple Sources
Bild der Seite - 139 -
Text der Seite - 139 -
5.1. Verification inHEPHAISTOS
of heating sources does not have any influences to this stability. Re-
sults from the first and the second steps prove that HEPHAISTOS is
a non-stochastic system. The dynamics of HEPHAISTOS are possible
to be modeled and learned via repeated experiments and tests, which
provides a solid foundation to all previous introduced modeling and
controlmethods.
Step3: Validityof linearandnonlinearmodels
In the last verification step, the previously mentioned principle of
heating rates is utilized, to verify if models 3.41 and 3.46 are accu-
rate approximations of practical heating situations. In order to get a
more comprehensive result, more temperatures were included in the
following verification experiment such as in figure 5.8 . Correspond-
ingVerificationproceduresaredescribedas infigure 5.9.
It is easy to test the linear superposition rule, by comparing the lin-
earlysuperposedheatingrateRlinearwiththerealoverallheatingrate
Rreal. If the linear superposed heating rate Rlinear is equivalent to
the real heating rateRreal, it means that the linear superposed power
also equals to the practical overall heating power, and consequently,
it proves the validity of the linear model 3.41 . The corresponding
verification result for two different feeding sources is shown in the
followingfigure 5.10 .
From the above figure it is noted that the linear superposed heating
rate Rlinear is close to the real heating rate Rreal. For situations with
moresources, thesameresult stillholds 5.11.
(a)Trial1at time t=2s (b)Trial2at time t=2s (c)Trial3at time t=2s
139
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