Page - 108 - in Adaptive and Intelligent Temperature Control of Microwave Heating Systems with Multiple Sources
Image of the Page - 108 -
Text of the Page - 108 -
4. ControlSystemDesign
control isdefinednotonlybycharacterizingappliedcontrolmethods,
but also by characterizing the control task being optimized. In other
words, the control task used in the intelligent control system is also
”intelligent”. The so-called intelligent control task is named in com-
parison with traditional control tasks. In conventional heating prob-
lems, the mean square error (MSE) between measured temperatures
and the target temperature is used as the cost (objective) function of
thecontrol task,suchasequation 4.2usedintheMPCmethod.
In many cases, the expression 4.2 is not always the best choice for the
cost function. On the one hand, the true temperature distribution is
not well represented by the value of the cost function. For example,
during the heating process, there are a number of hot spots and cold
spots that are not measured, and thus not reflected by the value of
the cost function (equation 4.2). On the other hand, in applications
where the entire temperature profile is available, only a small part of
theprofileisusedinthecontrolof thecost function 4.2. Themostpart
of the informationfromthethermalpicture iswasted.
Initializeweightsof theNNcontrollerandtheNNestimator
aswc andwe;
Initialize functionsof theNNcontrollerandtheNNestimator
asGandF;
Set theestimationerror indicatorχindandits lower thresholdχth;
Set theparametersc(k),α(k), thecounternumberCt= 1andthe
indirect trainingtimernt= 1;
Take thefirst controlactionasU(k) =Fc(Y(k),Ytar(k))at timek= 1;
Figure4.7. Procedures in thesemi-directNNcontrol system(part1).
In this case, it is better to replace the traditional cost function by more
innovative and reliable definitions, which are the intelligent control
tasks as previously mentioned. For example, using a infrared camera
to measure the temperature profile of the heated load, the maximum
and the minimum temperatures of the whole heated loadYmax,Ymin
can be obtained in real time, and a more reliable cost function can be
108
back to the
book Adaptive and Intelligent Temperature Control of Microwave Heating Systems with Multiple Sources"
Adaptive and Intelligent Temperature Control of Microwave Heating Systems with Multiple Sources
- Title
- Adaptive and Intelligent Temperature Control of Microwave Heating Systems with Multiple Sources
- Author
- Yiming Sun
- Publisher
- KIT Scientific Publishing
- Location
- Karlsruhe
- Date
- 2016
- Language
- English
- License
- CC BY-SA 3.0
- ISBN
- 978-3-7315-0467-2
- Size
- 14.8 x 21.0 cm
- Pages
- 260
- Keywords
- Mikrowellenerwärmung, Mehrgrößenregelung, Modellprädiktive Regelung, Künstliches neuronales Netz, Bestärkendes Lernenmicrowave heating, multiple-input multiple-output (MIMO), model predictive control (MPC), neural network, reinforcement learning
- Category
- Technik