The universal islanding detection methods (IDMs) for photovoltaic (PV) power systems require manually thresholds setting. That will lead to a certain non-detection zone (NDZ). Moreover, disturbance signals injected by...
详细信息
The universal islanding detection methods (IDMs) for photovoltaic (PV) power systems require manually thresholds setting. That will lead to a certain non-detection zone (NDZ). Moreover, disturbance signals injected by active detection methods may adversely affect power quality. Aiming at the above problems, this study proposes a passive intelligent IDM for parallel multi-PV system based on improvedadaptiveboosting (Adaboost) algorithm. Using Adaboost algorithm to generate classification models for islanding detection can theoretically avoid the NDZ of passive methods. The proposed method takes advantage of the electrical connection between characteristic parameters to adjust the classification model and improves the detection ability by redistributing the weight of each sub-model. Simulation results show that when adopted to a multi-PV system, the proposed method can effectively distinguish islanding operation in the NDZs of conventional passive IDMs. The method can also achieve accurate detection in the case of short-term power quality interferences, line faults and disturbance signal interference injected by active methods.
The accurate identification of rolling bearing fault based on unbalanced data has always been a challenge in the field of fault diagnosis. In some practical scenarios, since the machine is in the normal state most of ...
详细信息
The accurate identification of rolling bearing fault based on unbalanced data has always been a challenge in the field of fault diagnosis. In some practical scenarios, since the machine is in the normal state most of the time, data imbalance will inevitably be encountered. For this purpose, a deep ensemble dense convolutional neural network (DEDCNN) is developed in this paper. First, dense convolutional neural network (DCNN) is used as a basic classifier to learn representative features. A striking characteristic of DCNN is that the learned features of each layer can be reused by all subsequent layers. Second, an adaptiveboostingalgorithm is used to integrate multiple DCNN classifiers to construct a DEDCNN. Third, the parameter transfer training mechanism of an improved adaptive boosting algorithm is designed and applied to the DEDCNN, in which the learned parameter information of the ith DCNN classifier is transferred to train the (i + 1)th DCNN classifier, in order to speed up the training process and improve diagnostic ability. Extensive data imbalance experiments are conducted to demonstrate the effectiveness of the proposed method. The results demonstrate that the proposed method exceeds the capabilities of the existing approaches.
暂无评论