Forecasting Breakdowns of Electric Motors of a Sugar Factory Using Machine Learning Methods

the paper demonstrates the process of developing mathematical models for identifying breakdowns of electric motors using machine learning methods. The authors have developed three mathematical models for identifying breakdowns of electric drives with a power of 55 kW, 1500 rpm on the example of sugar production: model for quadratic discriminant analysis; binary classification decision tree; feed-forward neural network model. The best structures and parameters of the models were determined by machine learning methods. The performance of the models on the training and test sets was more than 96% by F-score. It was proposed to use all three models independently for diagnosing breakdowns of electric drives, while the decision maker makes the final decision on the replacement or repair of electrical equipment. This approach is justified and effective because of the diversity of models. The developed models, except for assessing the state of the engine, can also be used for simulation modelling, forecasting, and serve as information support for process operators in organizing equipment maintenance. The availability of real-time information about the state of equipment in production will allow timely repair or replacement of equipment, thereby reducing the risks of stopping production and increasing the resource efficiency of technological processes.