This research paper proposes the percentage of Silica is measured in a lab experiment it takes at least one hour for the process engineers to have this value. As this impurity is measured every hour and it takes a lot of time for a day and causes delay in the mining process. The environment is polluting while reducing the number of ore that goes to tailings as you reduce silica in the ore concentrate. The overall goal is to predict impurity in the ore concentrate in mining process. In this case impurity is specifically Silica concentrate. Silica concentrate is a measured variable but takes time to report results, thus reducing efficiency in the mining process. Being able to predict the silica content without stopping to test is the extended goal of this project. This appears to be a continuous batch process, where raw material is fed into a flotation system, processed, removed, and the process repeated. The purpose is to evaluate the feasibility of using machine learning algorithms like Multiple Linear Regression, Random Forest and Decision tree to predict in real-time. And also, by using Deep Learning techniques like LSTM, we can predict the silica impurity in the ore in less time and help the engineers for early prediction and reduce the impurities. We also developed a web application to display the prediction. The web application is built by using flask framework and it is integrated with trained ML model and it help the engineers, giving them early information to take actions (empowering!).Hence, they will be able to take corrective actions in advance (reduce impurity, if it is the case) and also help the environment.
