Seite - 153 - in Adaptive and Intelligent Temperature Control of Microwave Heating Systems with Multiple Sources

5.2. ResultsofSystemIdentification 0 2 0 0 4 0 0 6 0 0 8 0 0 1 0 0 00 5 1 0 1 5 2 0 T i m e ( s ) E K FB P MS W B P (b)Comparisonof thestandarddeviation. Figure5.16. Validationresultsof threealgorithms. Algorithm LearningMSE MeanSDof validation Time(per update) EKF 0.1172 0.7743 0.0031s BPM 0.0990 9.8806 0.0015s SWBP 0.0974 10.4665 0.3446s Table5.2. Performancecomparisonof threeonlineNNtrainingalgorithms. to the highest estimation accuracy and more comprehensive perfor- mance, the EKF algorithm is applied in the NNC system to train the systemestimator. Performance of both grey-box and black-box approaches can be com- pared qualitatively according to above results. On the one hand, both linearandnonlinearon-linerecursivesystemidentificationalgorithms havefastconvergingspeedthantheNNapproaches. Butontheother 153