Artificial Intelligence and Machine Learning using NI AutoML in Industry - Case Study: Simulated Waveforms

Nowadays, Artificial Intelligence and Machine Learning is everywhere, and everyone wants to use it. This paper presents a case study on how to use NI AutoML application to more easily solve a waveforms prediction problem. NI AutoML is a web application that allows layman, and also data scientist, to train Artificial Intelligence and Machine Learning models as a self-service. The paper presents a simple and basic example that can be further developed and add more complexity on top of it for being applied in real industrial problems such as the battery industry where in the test step the current and the voltage are measured and analyzed to know if the battery is good or bad. The presented case study is just a simple example of this complex problem. Instead of data from the battery, it used data from an RL simulated circuit and obtained waveforms from current and voltage. The data was loaded into NI AutoML and created a prediction model, that was used in NI SystemLink Enterprise into Jupyter Notebook for calculating the prediction for new data that arrived into the system and in the end, all the predicted results are presented into one NI SystemLink Dashboard.