Real-Time Diagnosis Based on Signal Convolution-Pooling Processing and Shared Filter Learning for Transistor Open-Circuit Faults in a T-Type Inverter

Keyphrases

• Transistor 100%
• Filter Learning 100%
• Convolution Feature 100%
• Feature Classifier 100%
• T-type Inverter 100%
• Open-circuit Fault 100%
• Neural Network 60%
• Real-time Fault Diagnosis 40%
• Current Signal 20%
• Feature Map 20%
• Inputs Channels 20%
• Reconstruction Strategy 20%
• Diagnostic Accuracy 20%
• Diagnostic Process 20%
• Data-driven Methods 20%
• Fault Diagnosis 20%
• Load Change 20%
• Multi-signal 20%
• Limited Training Data 20%
• Testing Time 20%
• Filter Parameter 20%
• Processing Function 20%
• Sequence Reconstruction 20%
• Multiple Time Series 20%
• Diagnostic Signal 20%
• Fault Characteristics 20%
• Feature Processing 20%
• Global Average Pooling Layer 20%
• Three-phase Current 20%

Engineering

• Open Circuit 100%
• Fault Diagnosis 100%
• Circuit Faults 100%
• Inverter 100%
• Current Signal 33%
• Feedforward 33%
• Testing Time 33%
• Input Feature 33%
• Filter Parameter 33%
• Channel Count 33%

Chemical Engineering

• Auxiliaries 100%
• Neural Network 100%