With the assumption of sufficient labeled data, deep learning based machinery fault diagnosis methods show effectiveness. However, in real-industrial scenarios, it is costly to label the data, and unlabeled data is underutilized. Therefore, this paper proposes a semi-supervised fault diagnosis method called Bidirectional Wasserstein Generative Adversarial Network with Gradient Penalty (BiWGAN-GP). First, by unsupervised pre-training, the proposed method takes full advantage of a large amount of unlabeled data and can extract features from vibration signals effectively. Then, using only a few labeled data to conduct supervised fine-tuning, the model can perform an accurate fault diagnosis. Additionally, Wasserstein distance is used to improve the stability of the model’s training procedure. Validation is performed on the bearing and gearbox fault datasets with limited labeled data. The results show that the proposed method can achieve 99.42% and 91.97% of diagnosis accuracy on the bearing and gear dataset, respectively, when the size of the training set is only 10% of the testing set.
The quality of visual feature representation has always been a key factor in many computer vision tasks. In the person re-identification (Re-ID) problem, combining global and local features to improve model performance is becoming a popular method, because previous works only used global features alone, which is very limited at extracting discriminative local patterns from the obtained representation. Some existing works try to collect local patterns explicitly slice the global feature into several local pieces in a handcrafted way. By adopting the slicing and duplication operation, models can achieve relatively higher accuracy but we argue that it still does not take full advantage of partial patterns because the rule and strategy local slices are defined. In this paper, we show that by firstly over-segmenting the global region by the proposed multi-branch structure, and then by learning to combine local features from neighbourhood regions using the proposed Collaborative Attention Network (CAN), the final feature representation for Re-ID can be further improved. The experiment results on several widely-used public datasets prove that our method outperforms many existing state-of-the-art methods.
The classification performance of the classifier is weakened because the noise samples are introduced for the use of unlabeled samples in Tri-training. In this paper a new Tri-training style algorithm named AR-Tri-training (Tri-training with assistant and rich strategy) is proposed. Firstly, the assistant learning strategy is posed. Then the supporting learner is designed by combining the assistant learning strategy with rich information strategy. The number of mislabeled samples produced in the iterations of three classifiers mutually labeling are reduced by use of the supporting learner, moreover the unlabeled samples and the misclassified samples of validation set can be fully used. The proposed algorithm is applied to voice recognition. The experimental results show that AR-Tri-training algorithm can compensate for the shortcomings of Tri-training algorithm, further improve the testing rate.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.