Complexity

Research Article

Power Loss Prediction for Aging Characteristics and Condition Monitoring for Parallel-Connected Power Modules Using Nonlinear Autoregressive Neural Network

Table 4

The evaluation criteria for condition.
The error between the predicted and measured power lossesWhich error is the leastThe degradation grade
Error0-Model-0 ()If this one is the leastNormal
Error1-Model-1 ()If this one is the leastSlight aging I
Error2-Model-2 ()If this one is the leastSlight aging II
Error3-Model-3 ()If this one is the leastSerious aging I
Error4-Model-4 ()If this one is the leastSerious aging II