An Intelligent Fault Detection Method of Industrial Gearboxes With Robustness One-Class Support Matrix Machine Toward Multisource Nonideal Data

Various kinds of sensing data can be acquired for smart fault detection. Each signal source has spatial attributes and strong correlations exist between different data sources. However, most of the existing fault detection models are established in the vector domain, which would destroy the structure information embedded within multisource data. Besides, the nonideal data, especially strong-noise data and mislabeled data, will seriously affect the fault detection performance. Therefore, a matrix-form one-class model called robustness one-class support matrix machine (ROCSMM) is proposed for industrial gearbox fault detection under multisource nonideal data. ROCSMM extends the traditional one-class support vector machine to the matrix domain, which can retain the topological structure information of multisource data while improving the fault detection performance. Besides, an adaptive weight generation strategy is designed for ROCSMM according to the prior distribution of matrix samples. This strategy can eliminate the negative impact of nonideal data on ROCSMM to the greatest extent and improve the model's robustness. The experimental results indicate that the proposed model is superior to other cutting-edge models in the fault detection of industrial gearboxes.