No abstract

No abstract

Intelligent fault diagnosis methods based on deep learning have achieved much progress in recent years. However, there are two major factors causing serious degradation of the performance of these algorithms in real industrial applications, i.e., limited labeled training data and complex working conditions. To solve these problems, this study proposed a domain generalization-based hybrid matching network utilizing a matching network to diagnose the faults using features encoded by an autoencoder. The main idea was to regularize the feature extractor of the network with an autoencoder in order to reduce the risk of overfitting with limited training samples. In addition, a training strategy using dropout with random changing rates on inputs was implemented to enhance the model’s generalization on unseen domains. The proposed method was validated on two different datasets containing artificial and real faults. The results showed that considerable performance was achieved by the proposed method under cross-domain tasks with limited training samples.

No abstract

In this paper, we propose a broad learning system based on the sparrow search algorithm. Firstly, in order to avoid the complicated manual parameter tuning process and obtain the best combination of hyperparameters, the sparrow search algorithm is used to optimize the shrinkage coefficient (r) and regularization coefficient (λ) in the broad learning system to improve the prediction accuracy of the model. Second, using the broad learning system to build a network interface flow forecasting model. The flow values in the time period [T−11,T] are used as the characteristic values of the traffic at the moment T+1. The hyperparameters outputted in the previous step are fed into the network to train the broad learning system network traffic prediction model. Finally, to verify the model performance, this paper trains the prediction model on two public network flow datasets and real traffic data of an enterprise cloud platform switch interface and compares the proposed model with the broad learning system, long short-term memory, and other methods. The experiments show that the prediction accuracy of this method is higher than other methods, and the moving average reaches 97%, 98%, and 99% on each dataset, respectively.