HealthMachina is a web-based application that we designed using Python, Flask, HTML, and CSS to predict potential machinery failures in industrial settings. The core of the project is a machine learning model built in Python, which utilizes the scikit-learn library for data preprocessing and training. we employed the RandomForest classifier to predict failures, achieving a high accuracy of 98%.
The website is designed with HTML and CSS, ensuring a clean and responsive user interface. Flask was used to seamlessly integrate the machine learning model with the website, allowing users to input the current physical conditions of machinery and receive predictions on possible failures. The project code breakdown is as follows: 46% Python for the model, 41% HTML for the front-end design, and 13% CSS for styling.
This project demonstrates my proficiency in full-stack development and machine learning, combining web technologies with predictive analytics to create a practical tool for industry applications.