A feature extraction method for rotating machinery fault diagnosis based on a target detection index and successive variational mode decomposition

Rotating machinery feature extraction is critical for the subsequent fault diagnosis and ensuring safe and stable operation. However, the commonly used methods often have limitations, such as the extracted features being redundant or insufficient and the method parameters generally being set based on experience. Although some feature extraction methods apply optimization algorithms for parameter setting, their objective functions are often too simple to obtain favorable fault diagnosis results. To address these issues, a target detection index (TDI) is constructed which can consider the discrimination among features more comprehensively and make the extracted features more sensitive. Furthermore, a fault feature extraction method is proposed based on TDI and successive variational mode decomposition (SVMD). Taking TDI as the objective function, genetic algorithm (GA) is used for the feature selection process and SVMD parameter optimization. The obtained features are then fused and visualized using t-distributed stochastic neighbor embedding and are classified using support vector machines. The Case Western Reserve University data and hydropower generating unit data are employed for method verification. When compared with other decomposition algorithms, the proposed method exhibits great ability at extracting highly sensitive features.