EXPERIMENTAL INVESTIGATION ON THE USE OF VIBRATION SIGNALS COMBINED WITH SUPERVISED CLASSIFICATION TO PREDICT RADIAL LOAD CONDITION IN ROLLER ELEMENT BEARINGS

Keyphrases

• Loading Conditions 100%
• Vibration Signal 100%
• Supervised Classification 100%
• Radial Load 100%
• K-nearest 33%
• Vibration Response 33%
• Operating Conditions 16%
• Selection Strategy 16%
• Machine Learning Algorithms 16%
• Time-frequency 16%
• Fatigue Crack 16%
• Fast Fourier Transform 16%
• Low Threshold 16%
• Dynamic Response 16%
• High Stress 16%
• Piezoelectric Accelerometer 16%
• Running Speed 16%
• Training Data 16%
• Statistical Techniques 16%
• Spectral Components 16%
• Loading Rate 16%
• Wavelet Transform 16%
• Wavelet 16%
• High Threshold 16%
• Rotor Speed 16%
• Classification Results 16%
• Statistical Measures 16%
• Roller Bearing 16%
• Accelerometer Sensor 16%
• Feature Subset 16%
• Multi-fold 16%
• Cyclic Dynamics 16%
• Bearing Elements 16%
• Reduced Feature Set 16%
• Rolling Element Bearing 16%
• Training Phase 16%
• Operating Load 16%
• Vibration Signature 16%
• Subset Selection 16%
• Bearing Assembly 16%
• Feature Reduction 16%
• Wavelet Approximation 16%
• Radial Measure 16%
• Spall 16%

Engineering

• Experimental Investigation 100%
• Load Condition 100%
• Radial Load 100%
• Bearing Element 100%
• Feature Extraction 50%
• Extracted Feature 50%
• Radial Basis Function 50%
• Nearest Neighbor 50%
• Support Vector Machine 50%
• Piezoelectric 25%
• Recursive 25%
• Fatigue Crack 25%
• Fast Fourier Transform 25%
• Selection Method 25%
• Rotor Speed 25%
• Running Speed 25%
• Dynamic Response 25%
• Spectral Component 25%
• Test Rig 25%
• Load Speed 25%
• Machine Learning Algorithm 25%
• Neighbor Classifier 25%
• Rolling Element 25%
• Accelerometer Sensor 25%