Study on Soft-Sensing Model of Tower Crane Load Based on Functional Link Neural Network

The nonlinear relation between the load and the force of sensor in soft-sensing of tower crane load is indicated by force analysis of load limiter. This paper proposes a soft-sensing model based on functional link neural network (FLNN) with the force of sensor as input and the load as output. By adding some high-order terms, the model applies the single-layer network to realize the network supervised learning. The approach has advantages of nonlinear approach ability and independent on accurate mathematical model, it can improve network learning speed and simplify the network structure, and provides a new method for on-line measurement of tower crane load. The implementation process of FLNN about tower crane QTZ63 is presented, the experimental research show that the maximum relative error of measured load is less than 2.1% and can satisfy the National standard GB5144-94.