Spectrum Analysis of Mixing Power Curves for Neural Network Prediction of Dough Rheological Properties

Two spectrum analysis techniques, namely Fast Fourier Transform (FFT) and power spectral density (PSD),were used for data preprocessing as part of development of neural networks for prediction of the rheological properties ofa cookie dough. The raw data were extracted from the mixing power consumption curves acquired during mixing of thedough. The rheological properties studied were farinograph peak, extensibility and maximum resistance. Two types ofneural networks, namely back propagation (BP) and general regression neural network (GRNN) with differentarchitectures were developed for this study. The prediction accuracy of these networks when trained with the raw data, orFFT or PSD treated data was evaluated. The results indicate that the FFT and PSD treated data retained most of thecharacteristics of the raw data but with reduced noise and size. The performance of the networks trained with FFT orPSD treated data was found to be comparable with that of the networks trained with the raw data. For the BP network,the FFT treatment slightly improved the network performance while the PSD treatment resulted in a slightly higher butacceptable APE. It was noted that the farinograph peak and extensibility were better predicted than the maximumresistance by the neural network techniques. The prediction of maximum resistance was greatly improved by using aGRNN trained with the FFT or PSD treated data. It is therefore concluded that the spectrum analysis techniques used inthe study can greatly improve the efficiency of the neural networks for the prediction of dough rheology while preserveprediction accuracy.