An Improved Prediction Model of IGBT Junction Temperature Based on Backpropagation Neural Network and Kalman Filter

<div>(a) The comparison of errors when <svg height="11.927pt" id="M48" style="vertical-align:-3.291101pt" version="1.1" viewbox="-0.0498162 -8.6359 11.5182 11.927" width="11.5182pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M405 650H141L135 622C222 616 230 610 215 535L133 116C118 41 113 33 29 28L23 0H289L295 28C209 33 205 40 219 116L298 535C312 609 317 616 399 622L405 650Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,4.719,3.132)"><path d="M690 629C653 643 577 667 483 667C225 667 24 528 24 292C24 92 174 -17 367 -17C448 -17 534 1 570 10C592 34 642 131 658 174C648 180 639 186 629 192C562 89 499 21 382 21C223 21 130 138 130 298C130 467 255 627 462 627C582 627 643 589 650 462L686 466C689 517 688 580 690 629Z"></path></g></svg> &lt; 42 A. (b) The comparison of errors when <svg height="11.927pt" id="M49" style="vertical-align:-3.291101pt" version="1.1" viewbox="-0.0498162 -8.6359 11.5182 11.927" width="11.5182pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M405 650H141L135 622C222 616 230 610 215 535L133 116C118 41 113 33 29 28L23 0H289L295 28C209 33 205 40 219 116L298 535C312 609 317 616 399 622L405 650Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,4.719,3.132)"><path d="M690 629C653 643 577 667 483 667C225 667 24 528 24 292C24 92 174 -17 367 -17C448 -17 534 1 570 10C592 34 642 131 658 174C648 180 639 186 629 192C562 89 499 21 382 21C223 21 130 138 130 298C130 467 255 627 462 627C582 627 643 589 650 462L686 466C689 517 688 580 690 629Z"></path></g></svg> &gt; 42 A.</div>

Complexity

fig11

Figure 11

Figure 11: An Improved Prediction Model of IGBT Junction Temperature Based on Backpropagation Neural Network and Kalman Filter 