SEFormer: A Lightweight CNN-Transformer Based on Separable Multiscale Depthwise Convolution and Efficient Self-Attention for Rotating Machinery Fault Diagnosis
Hongxing Wang, Zhu Hua, Huafeng Li, Xilai Ju
2024Computers, materials & continua/Computers, materials & continua (Print)11 citationsDOIOpen Access PDF
Abstract
Traditional data-driven fault diagnosis methods depend on expert experience to manually extract effective fault features of signals, which has certain limitations. Conversely, deep learning techniques have gained prominence a... | Find, read and cite all the research you need on Tech Science Press
Topics & Concepts
Separable spaceTransformerComputer scienceConvolution (computer science)Fault (geology)AlgorithmArtificial intelligenceEngineeringMathematicsElectrical engineeringMathematical analysisVoltageGeologyArtificial neural networkSeismologyMachine Fault Diagnosis TechniquesNon-Destructive Testing TechniquesUltrasonics and Acoustic Wave Propagation