Description: A learning algorithm is proposed in this paper by analyzing the error function of neural network ensembles, in which individual neural networks are actively guided to learn diversity. By decomposing the ensemble error function, error correlation terms are included in the learning criterion function of individual networks. And all the individual networks in the ensemble are leaded to learn diversity through cooperative training. The method is applied in fault diagnosis of power transformer based on Dissolved Gas Analysis. Experiment results show that, the algorithm has higher accuracy than IEC method and BP network. And the performance is more stable than conventional ensemble method, i.e., Bagging and Boosting.
To Search:
File list (Check if you may need any files):
ADL方法code
...........\classdata.m
...........\classtraindata.m
...........\data.m
...........\dt_nne_simple.m
...........\dt_nne_vote.m
...........\dt_nne_winner.m
...........\fault_all_data.txt
...........\fault_bagging_NNE.m
...........\fault_bagging_bp.m
...........\fault_boosting_NNE.m
...........\fault_bpnet.m
...........\fault_data.m
...........\fault_data3.m
...........\fault_data3.txt
...........\iec.m
...........\irisdataset1.m
...........\nne_corr.m
...........\nne_simple.m
...........\nne_vote.m
...........\nne_winner.m
...........\trainset.m
...........\trainset1.m
...........\trainset2.m
...........\trainset3.m
...........\trainset4.m
...........\trainset5.m
Download