Detection of malfunctions and abnormal operating conditions of a coal mill
Teres Bil , Konrad Wojdan , Dominik Nabagało , Konrad Świrski
AbstractAbstract This work presents the proposal of an algorithm focused on detecting coal mill malfunctions and periods of unusual working conditions. First part gives theoretical background. It presents typical coal mill constructions and the idea of predictive maintenance, describes currently developed methods and techniques used for prediction of coal mill malfunctions. Second part describe in details the whole process of creation such algorithm. This process consist of 3 crucial phases. Phase one is focused on proper data collection, data preparation, analysis of data distributions and examination of existing correlations between them. Phase two is focused on choosing and developing proper model that describes work of coal mill. In this work it is chosen to develop model based of linear regression theory, therefore this phase is mainly focused on proper feature selection on
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.