Bearing fault diagnosis model based on MCNN-LSTM

Using knowledge-informed machine learning on the PRONOSTIA (FEMTO) and IMS bearing data sets. Predict remaining-useful-life (RUL).

This repository contains data and code that implement common machine learning algorithms for machinery condition monitoring task.

Siamese network for bearing fault diagnosis

Bearing fault detection public datasets collection.

Benchmark code for optimizers of bearing fault diagnosis. This code provides moduled features of data download, preprocessing, training, and logging.

wdcnn model for bearing fault diagnosis

Improving on NASA's work with induction motor bearing fault detection using RNN-powered smart sensors.

Deep learning models (RNN & LSTM & WaveNet) for predicting the remaining useful life of rolling element bearings using time series health indicators. Compares performance between different architectures for predictive maintenance applications.

Bearing Fault Detection and Classification Based on Temporal Convolutions and LSTM Network in Induction Machine Systems

AI-Powered Predictive Maintenance & Fault Diagnosis through Model Context Protocol. An open-source framework for integrating Large Language Models with predictive maintenance and fault diagnosis workflows.

Simulation and Modeling in Python 3

Vibration analysis tool, Signal processing tool

A machine learning project for classifying bearing faults using the CWRU dataset, with models built using Python and various ML techniques such as cross-validation, PCA, tSNE, SVM, XGBoost.

Cyclostationary analysis in angular domain for bearing fault identification

Showcase how machine learning can help plant operator monitor equipment condition through correctly analyzing measurement data collected from many sensors.

Detection of defective rolling bearings with machine learning methods based on bearings acceleration data

This project uses Explainable AI (XAI) to interpret machine learning models for diagnosing faults in industrial bearings. By applying SVM and kNN models and leveraging SHAP values, it enhances the transparency and reliability of machine learning in industrial condition monitoring.

Diagnóstico de falla de rodamiento utilizando descomposición modal empírica y deep learning

Long short-term memory based semi-supervised encoder-decoder for early prediction of failures in self-lubricating bearings

A deep learning fault classification model for wind turbine drivetrain bearings using combined PCA-CNN approach

Researches dedicated to bearing fault diagnosis from Mandevices Laboratory

Contest solution for 数境创新大赛-先进制造制造关键装置故障诊断

the PLS allows both to classify the types of faults and to reduce the dimensionality of the problem by trying to maximize the covariance between X and Y, useful in supervised learning.

NASA Bearing Dataset: Fault Detection with Wiener denoising and custom time-frequency btstft Transforms

This is a reository to share my studys in machine learning, data science & artificial intelligence

Unsupervised novelty detection for industrial bearing fault diagnosis using machine learning. Includes implementations of Isolation Forest, LOF, One-Class SVM, and ISO 20816 threshold methods on real experimental data from medium-sized spherical roller bearings.

Bearings_damage_classifier_model

Fault Bearing Classification Analysis dashboard to explore, diagnose and highlight potential factors to predict the fault class based on bearing statistical manufacturing data.

This research is conducted as part of the NSBE Aerospace SIG internship program. It is focused on investigating The Feasibility of Implementing Predictive maintenance on Rotorcraft Health and Usage Monitoring Systems.