Predictive value feedback retraining strategy and application for autoregressive neural networks
To improve the multi-step prediction performance of nonlinear autoregressive neural network(NARX-NN),a predictive value feedback retraining(FR)strategy was proposed.Initially,the NARX-NN was trained using conventional training strategies.Then,the training samples were reconstructed by replacing the measured values with the one-step predicted values,which were used to train the network again.To vali-date the effectiveness of FR,it was applied to three typical NARX-NN models:nonlinear autoregressive deep neural network(NARX-DNN),encoder-decoder based on long short-term memory network(LSTMED)and deep autoregressive network(DeepAR)for predicting the NOx mass concentration of coal-fired boilers or the electrical load of integrated energy system.Comparison results with conventional training strategies and sched-uled sampling show that NARX-NN with FR has the highest multi-step prediction accuracy,with a mean abso-lute percentage error(MAPE)of 4.01％for LSTMED for 15-step forward prediction of NOx mass concentra-tion and 4.34％for DeepAR for 24-step forward prediction of electrical loads.The results of paired-sample T-test indicate that FR improves the multi-step prediction performance of NARX-NN significantly.By keeping the consistency of the inputs in the training and prediction phases,FR effectively improves the multi-step pre-diction accuracy of the NARX-NN model.
neural networkmulti-step predictiontraining strategyNOx mass concentrationelectrical loads
万方数据
维普
