Application of neural network method to detect type of uranium contamination by estimation of activity ratio in environmental alpha spectra

The discrimination of the composition of environmental and non-environmental materials by the estimation of the 234U/238U activity ratio in alpha-particle spectrometry is important in many applications. If the interfering elements are not completely separated from the uranium, they can interfere with the determination of 234U. Thickness as a result of the existence of iron in the source preparation phase and their alpha lines can broaden the alpha line of 234U in alpha spectra. Therefore, the asymmetric broadening of the alpha line of 234U and overlapping of peaks make the analysis of the alpha particle spectra and the interpretation of the results difficult. Applying Artificial Neural Network (ANN) to a spectrometry system is a good idea because it eliminates limitations of classical approaches by extracting the desired information from the input data. In this work, the average of a partial uranium raw spectrum, were considered. Each point that its slope was of the order of 0-1% per 10 channels, was used as input to the multi-layer feed forward error-back propagation network. The network was trained by an alpha spectrum library which has been developed in the present work. The training data in this study was actual spectral data with any reasonable thickness and interfering elements. According to the results, the method applied to estimate the activity ratio in this work, can examine the alpha spectrum for peaks which would not be expected for a source of given element and provide the clues about composition of uranium contamination in the environmental samples in a fast screening and classifying procedures.