• Gokul s
• Madhorubagan E
• Dr.Singaravel G

The project describes the design and implementation of a non-contact vibration picker for capturing data from spinning machinery in order to detect bearing faults early. The Hilbert transform is used to denoise the collected vibration signals, and the dataset is then analyzed by Principal Component Analysis (PCA) and Sequential Floating Forward Selection (SFFS) for dimensionality reduction and feature selection, respectively. The most essential attributes are then used to identify and categorize various bearing issues using Support Vector Machines (SVM) and Artificial Neural Network (ANN) algorithms. The entire methodology provides an effective and proactive way for bearing health monitoring and maintenance, emphasizing fast defect identification and leading to significant savings in time, effort, and equipment maintenance costs.

Machine Learning, Fault Prediction, Fuzzy Convolution Neural Network (FCNN), Heterogeneous Sensing Data Fusion

"FAULT PREDICTION USING FUZZY CONVOLUTION NEURAL NETWORK ON IOT ENVIRONMENT WITH HETEROGENEOUS SENSING DATA FUSION ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 6, page no.i407-i412, June-2024, Available :http://www.jetir.org/papers/JETIR2406842.pdf

"FAULT PREDICTION USING FUZZY CONVOLUTION NEURAL NETWORK ON IOT ENVIRONMENT WITH HETEROGENEOUS SENSING DATA FUSION ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 6, page no. ppi407-i412, June-2024, Available at : http://www.jetir.org/papers/JETIR2406842.pdf