A health management system for large vertical mill

Abstract

The large vertical mill has complicated structure and tens of thousands of parts, which is a critical grinding equipment for slag and cinder. As large vertical mill always works in severe conditions, the on-line monitoring, timely fault diagnosis, and trend prediction are very important guarantees for the safe service and saving maintaining costs. To address this issue, the health management system for large vertical mill is developed. More specifically, in order to manage reservoirs of state-related running data, the intrinsic physic data, and diagnosis knowledge base, an entity-relationship-model-based database is first constructed. Based on the fault diagnosis reasoning of experts, the fault tree is developed and the fault diagnosis rules are derived. Especially, a hybrid condition prognosis method based on backtracking search optimization algorithm and neural network is developed, and in comparison with traditional back propagation neural network and ant colony neural network, the developed backtracking search optimization algorithm and neural network gets superior hybrid prediction performance in prediction accuracy and training efficiency. Finally, the health management system, including the functions of condition monitoring, fault diagnosis, and trend prediction for large vertical mill is implemented using Microsoft Visual Studio C # and Microsoft SQL Server.