The On-Line Monitoring System of Tower Crane Load Based on FLNN

Abstract:

By force analysis of load limiter, the nonlinear relation between the load and the force of sensor in indirect measurement of tower crane load is indicated. Using the force of sensor as input and the load as output, the nonlinear correction model based on functional link neural network (FLNN) is proposed to eliminate the nonlinear errors of load measurement. By adding some high-order terms, the model uses the single-layer network to realize the network supervised learning. The approach can improve network learning speed and simplify the network structure, and provides a new way for On-line measurement of tower crane load. The system realization and network simulation about tower crane QTZ63 are presented, Practical application shows that the maximum relative error of measured load is less than 2.1% and can satisfy National standard GB5144-94.

• Periodical: Advanced Materials Research (Volumes 466-467)
• Pages: 1373-1377
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.466-467.1373
• Online since: February 2012
• Authors: Quan Min Guo, Hui Hu
• Keywords: Functional Link Neural Network, Nonlinear Correction, On-Line Monitoring System, Tower Crane Load

References

[1] J.Y. Wang, S.J. Song and Q. Zhang: Construction Machinery and Equipment, 12(2000), p.20.

[2] Z.X. Yan: Builder's Monthly, 1(2004), p.28.

[3] Q.M. Guo: Int. Conf. Inf. Technol. Comput. Sci., IEEE Computer Society, (2009), p.293.

[4] Pao Y.H. Adaptive Pattern Recognition and Neural Networks, Addission Wesly Press, (1988).

[5] Q.M. Guo, Y. F Jia and J. WANG: Network Instrument Technique and Sensor, 10(2007), p.33.

[6] W.J. Yue: Hoisting and conveying machinery, 3(2007), p.81.