Computational and Data Science Ph.D. student, Laurel Koenig, presents elements from their internship and research, Predictive Maintenance for heavy equipment with a classical and Quantum Support Vector Machine using novel data. This work shows the differences between quantum and classical machine learning on a real-world dataset
Predictive maintenance is the blanket term for methods used to maximize the lifetime of equipment by predicting when it will fail. Most predictive maintenance uses specialized sensors, but in this study we used a novel data set created from generalized equipment data that was already being collected from Caterpillar machines. We applied both classical and quantum support vector machines to predict machine failure. The classical machine used an RBF kernel with limited success. The quantum SVM utilized a trainable kernel that was formulated to be a RBF kernel as a baseline. The difference between the results of the classical and quantum algorithms is not statistically significant.