Dynamic load identification method of rock roadheader using multi neural network and evidence theory

摘要

As a part of automatic control system of rock roadheaders, the dynamic load identification is of great significance to improve the intelligent level and increase lifetime of roadheaders. In order to solve the problems of rock roadheaders such as complicated operating conditions, difficult dynamic load real-time identification, a recognition method based on multi-neural network and evidence theory is proposed. Dynamic load of rock roadheader is gained in real-time, combining vibration data, the current and hydraulic cylinder data, integrating two data fusion methods (ANN and evidence theory) by using their superiority and avoiding their disadvantages. It has been shown by experiments that the accuracy rate of dynamic load identification is up to 88% and the identification method can meet the requirement of dynamic load real-time identification system.