Intelligent Real-Time Monitoring System of Tower Crane Load Moment

Abstract

By analysis of working principle of elastic steel plate type load moment limiter, the nonlinear relation between the load moment and the horizontal displacement of moment limiter is indicated. This paper proposes a soft-sensing model based on functional link neural network (FLNN) with the horizontal displacement of moment limiter as input and the load moment as output. The model can apply the single-layer network to realize the network supervised learning by adding some high-order terms. The method can improve network learning speed and simplify the network structure, and provides a new way for On-line measurement of tower crane load moment. The Monitor System of Load Moment based on FLNN about tower crane QTZ5012 is presented, the practical application show that the monitoring system implements real-time display of load moment at a low cost and improves the safety in operation, the maximum relative error is reduced to 2.02% and can satisfy the National standard GB5144-94.