Fault Identification and Prediction of Yarn Machine Based on SVM and BAS-BP Diagnosis Algorithm

In order to accurately identify and predict yarn machine faults online, this paper proposes a fault identification and prediction model based on a small sample of fault data. Firstly, Ensemble Empirical Mode Decomposition (EEMD) is used to reduce the noise of the state data of the yarn machine, and the support vector machine (SVM) is adopted to establish a prediction model of the decomposed component sequence according to the feature set of the yarn machine. Secondly, the Beetle Antennae Search (BAS) is used to optimize the initial weights and thresholds of the BP neural network, which effectively solves the local optimal problem. Finally, the EEMD-SVM- BAS-BP model is compared and analyzed with the SVM-BP model. The experimental results show that the identification and prediction model proposed in this paper has high accuracy in yarn machine fault diagnosis.