This repository contains:-
📌 The readme file which describes what exactly this repository is about.
📌 Data set file on which ML algorithms are applied.
📌 The code section which contains all the code of various ML algorithms applied on the chosen dataset.
Detalied overview of the Dataset and Code section in the project:
The Dataset file is about electric motor temperature data in which there are 13 columns and the file is 300 MB in size. The main columns: 'stator_winding', 'stator_tooth', 'stator_yoke', and 'pm' are the temperatures of the motor and 'pm' is the column which we have to predict w.r.t all the remaining columns. The data set comprises several sensor data collected from a permanent magnet synchronous motor (PMSM) deployed on a test bench. The datset was taken from kaggle site.
◾ Here's the link for the dataset:- https://www.kaggle.com/wkirgsn/electric-motor-temperature
In this section there's a detailed code of performing a Machine Learning project at undergraduate level. Here I've performed Exploratory Data Analysis, Data Preprocessing and Visualization. Then after Data cleaning and formatting, I've applied Regression algorithms to train the model and predict the temperature ('pm') of the electric motor. Regression models like - Linear Regression, K-Nearest Neighbor Regressor, XGBoost Regressor and AdaBoost Regressor were used in this project. Also after visualizing the result and the evaluation table I've also performed cross-validation to validate each of my regression models and have plotted the comparison plots to conclude the best model for the motor temperature prediction.
◾ Find my complete code on kaggle:- https://www.kaggle.com/code/sukrutapardeshi/electric-motor-temperature-prediction-regression