Publication | Open Access
Vibration Anomaly Detection using Deep Neural Network and Convolutional Neural Network
10
Citations
0
References
2021
Year
Fault DiagnosisConvolutional Neural NetworkAnomaly DetectionMachine LearningNeural Networks (Machine Learning)EngineeringDiagnosisFault ForecastingVibration AnalysisHealth Monitoring (Structural Health Monitoring)Health Monitoring (Biomedical Engineering)Social SciencesCondition MonitoringVibrationsData SciencePattern RecognitionSystems EngineeringStructural Health MonitoringComputer ScienceNeural Networks (Computational Neuroscience)Deep LearningDeep Neural NetworkDeep Neural NetworksNovelty DetectionRandom VibrationVibration Anomaly Detection
Identifying the “health state” of the equipment is the domain of condition monitoring. The paper proposes a study of two models: DNN (Deep Neural Network) and CNN (Convolutional Neural Network) over an existent dataset provided by Case Western Reserve University for analyzing vibrations in fault diagnosis. After the model is trained on the windowed dataset using an optimal learning rate, minimizing the cost function, and is tested by computing the loss, accuracy and precision across the results, the weights are saved, and the models can be tested on other real data. The trained model recognizes raw time series data collected by micro electro-mechanical accelerometer sensors and detects anomalies based on former times series entries.