Fault Diagnosis of Pneumatic Control Valve Based on Unbalanced Data Set of GWO-SVM Model

In this paper, we explore the issue of pneumatic control valve using a model-based Support Vector Machine (SVM) classification approach. To solve the problem of poor performance of data-driven SVM on unbalanced data sets. Intelligent optimization algorithms based on artificial minority class oversampling (SMOTE) and grey wolf optimizer (GWO) are introduced to enhance the fault diagnosis performance of classification. Various comparisons have been performed utilizing a dataset of pneumatic control valve faults observed during sugar production at the Cukrownia Sugar Plant in Poland. The comparison results indicate that the proposed algorithm is better than the existing methods in classification.