Seite - 109 - in Adaptive and Intelligent Temperature Control of Microwave Heating Systems with Multiple Sources
Bild der Seite - 109 -
Text der Seite - 109 -
4.2. IntelligentControl
Ateach timek (k>1) :
repeat
1 Receive themeasuredtemperaturevectorY(k);
2 Calculate theestimationRMSEof theNN estimator asχ(k),
andupdate theestimationerror indexvia
χind= 0.95 ·χind+0.05 ·χ(k).
3 Update theweightsof theNNestimatorusing the EKF
algorithm;
if Mod(Ct,2) = 0 then
if χind < χth then
4 UsetheNNestimator to train the NN controller fornt
times togetnewwc(k)andupdate the training timer
nt=nt+1;
5 Calculate thenewcontrol input
U(k) =G(Ytar(k),Y(k),wc(k));
else
4 Reset the trainingtimernt= 1;
5 Calculate the trainingcontrol input as
w+(k) =w(k)+c(k)∆(k),
U(k) =U+(k) =G (
Yt(k),Y(k),w (+)(k) )
;
6 Update thecounternumberCt=Ct+1;
else
4 Update theweightsof theNNcontroller by
h(wc(k)) = J (
Y(k),U(+)(k) )
c(k)∆(k)
wc(k+1) =wc(k)−α(k) ·h(wc(k));
5 Update thecounternumberCt=Ct+1;
6 Calculate thenewcontrol input
U(k) =G(Ytar(k),Y(k),wc(k));
until the endof the controlprocess;
Figure4.7. Procedures in thesemi-directNNcontrol system(part2).
109
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