A functional relationship between two variables, applied mass to a weighing platform and estimated mass using Multi-Layer Perceptron Artificial Neural Networks is approximated by a linear function. Linear relationships and correlation rates are obtained which quantitatively verify that the Artificial Neural Network model is functioning satisfactorily. Estimated mass is achieved through recalling the trained Artificial Neural Network model on a set of waveforms resulting from applied masses over the operating range of the weighing platform. In this work the Least-Squares Fit (LSF) method for straight line and correlation rate R between the applied and estimated masses are used to investigate the accuracy of the estimated masses. The slope of the linear functions together with correlation rates R are computed for both simulation and experimental data. The numerical results confirm the correctness of neural network technique in estimating the applied mass m(t).
)