A Novel Arc Jointing Robot Scheduling Method in Electric Power Plants using Adaptive Neural Network and Fuzzy Reasoning

X. Chen and H. Xu (PRC)


Robot, Schedule, Neural Network, Fuzzy


Multi arc joint robot scheduling in jointing turbine is an important but difficult task in the construction and maintenance of turbines of electric power plants. In order to schedule the proper arc jointing robot when jointing turbines, this paper presents a novel multi robot scheduling approach on the base of Adaptive Artificial Neural Networks (NN). Feed forward, multi-layered neural network meta-models were trained through the back-error-propagation (BEP) learning algorithm to provide a versatile trajectory prediction of every robot. At the same time, a fuzzy reasoning based intelligent selection mechanism has been used to schedule the proper arc jointing robot assuring maximum utilization of resources and finally guaranteeing the high productivity. By testing the practical data set, the method is able to provide optimized solutions for practical robot scheduling problems. And it has the potential to be implemented in hardware with much improved quality and speed.

Important Links:

Go Back