Neural-network-based payload determination of a moving loader

This paper describes a method that combines a Kalman filter and neural network to form an efficient data fusion technique for estimating payload in the bucket of a moving loader. The Kalman filter is used to reduce the noise level in the measurement signals before the data are fed to the neural network. A neural network then represents the nonlinear connection between the indirect measurements describing the load and the actual load in the bucket. The results show that the combination of these different methods offers a viable solution for estimating the payload. (C) 2003 Elsevier Ltd. All rights reserved.