| Abstract [eng] |
The main problem to solve in this project – SC \"Volfas Engelman\" machines failure prediction estimation using artificial intelligence tools. The raised goal of the project – to carry out equipment failure prediction studies using selected artificial intelligence prediction methods and to assess the possibilities of the prediction accuracy. The analytical part provides an overview of equipment failures importance within the context of the production process and artificial intelligence capabilities. Selected artificial neural network, nearest neighbor, support vector machine and decision tree classification methods. The analysis of selected methods, characteristics of classification methods, implementation, accuracy rating is made. For experimental part beverage production facility objects characteristics (measured by devices) are selected and prepared failure event, type of failure, machine failure classes to recognize. |
