A new health indicator extracted by unsupervised learning using autoencoder in tandem with t-sne and multi-kernel CNN to enhance the early detection and classification of bearings multi-faults
Mohamed Zair, Chemseddine Rahmoune, Moussaoui Imane, Mahami Amine, Djamel Benazzouz
Topics & Concepts
AutoencoderComputer scienceArtificial intelligencePattern recognition (psychology)OverfittingFeature extractionConvolutional neural networkSupport vector machineDeep learningSmoothingNormalization (sociology)Machine learningArtificial neural networkComputer visionSociologyAnthropologyMachine Fault Diagnosis TechniquesFault Detection and Control SystemsQuality and Safety in Healthcare