| Title |
Real-Time Monitoring of Machine Learning for Robotic Perception: An Overview of Emerging Patterns |
| Abstract |
This project outlines the development and deployment of a non-contact vibration sensor designed to capture data from rotating machinery for early detection of bearing faults. The collected vibration signals undergo denoising using the Hilbert transform. Subsequently, Principal Component Analysis (PCA) and Sequential Floating Forward Selection (SFFS) are applied for dimensionality reduction and feature selection, respectively. The selected essential features are then utilized with Support Vector Machines (SVM) and Artificial Neural Networks (ANN) to detect and categorize various bearing issues. This comprehensive approach offers an efficient and proactive method for monitoring bearing health and maintenance, emphasizing rapid defect identification and resulting in significant time, effort, and equipment maintenance cost savings. |
| Keywords |
Machine Learning, Fault Prediction, Fuzzy Convolution Neural Network (FCNN), Heterogeneous Sensing Data Fusion |
| Reserch Area |
Engineering |
| Reserch Paper |
AIJFR2402002 - V2 I2 9-16 - Indonesia.pdf |
| Author(s) |
Saifeena Narul Afwah |
| Country |
Indonesia |
