This repo provides source code for cross-domain machine fault diagnosis using an unsupervised domain adaptation approach (Feature Representation Alignment Networks).

The project is a machine predictive maintenance application that uses machine learning (Random Forest) to classify whether a machine will experience failure or not based on various input parameters.

An implementation of DC-Prophet by Scikit Learn (Google-cluster-data catastrophe predicting), containing data preprocessing.

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.

Repository for Machine learning's semester project - Machine failure and failure type prediction using neural network.

Harness the power of Machine Learning to revolutionize industrial maintenance! This project leverages advanced ML algorithms to predict machinery failures, minimize downtime, and optimize maintenance schedules. By analyzing real-time data, our solution ensures proactive maintenance, enhancing operational efficiency and reducing costs.

Predicting failure of mechanical machines based of various sensor measurements and machine features/characteristics.

Predictive Maintenance for Machine Failure Detection using Machine Learning This project focuses on predicting machine failures using sensor data and machine learning techniques. By analyzing operational parameters like air pressure, temperature, rotational speed, and torque, the model identifies potential failures in advance.

Predicting Machine failure using Machine learning on a synthetic dataset of an existing milling machine consisting of 10,000 data points

Web app using the Poisson distribution to predict the number of machine failures.

Detecting Machine Failure from IoT Sensors with a SQL Pipeline.