Machine learning is hungry for data. In the immediate future one of our goals is to continue to improve our data acquisition and management techniques to ensure timely availability of sufficient quantities of good quality data for a given application. Drive System Design (DSD) is not unique in this quest; much of our industry is doing the same. What sets DSD apart is that, while most organizations are applying the technology to improve performance and functionality of products themselves, we have a twin-track approach in which we are also exploring its potential to improve the engineering design and development process as a whole.
Our latest research review uncovers our three key principles for applying machine learning in this way.