LabVIEW Integrated with Python Machine Learning for DC Motor Drive

This study presents a new technique that integrates LabVIEW and Python to enhance the control of DC motor drives through the utilization of machine learning methods. The objective of our research is to leverage LabVIEW’s graphical programming interface in combination with the Scikit-learn Python package to train a Polynomial Regression model. The goal is to forecast Pulse Width Modulation (PWM) values at desired Rotations per Minute (RPM) of a DC motor. The accuracy and reliability of the trained model are evaluated using performance assessment metrics such as the R-squared ($R^{\mathbf{2}}$) coefficient of determination and the Root Mean Square Error (RMSE). The $\mathbf{R}^{2}$ score assesses the precision of the model’s fit, whereas the RMSE quantifies the model’s predictive capability by comparing observed and predicted data. This research also includes a comparison between the machine learning technique for DC motor drive and conventional PID control. The findings illustrate the successful integration of LabVIEW and Python in managing DC motor drives, achieving low overshooting and faster attainment of the set RPM point compared to classical PID control. This emphasizes machine learning’s capacity to enhance control strategies; the application of Polynomial Regression yields promising results, demonstrating its effectiveness in predicting PWM and RPM values with an $R^{2}$ value ranging from 96% to 98% and RMSE within 19.