出版社：Faculty of Humanities, Kaunas University of Technology
其他摘要：Increasing concrete market and growing variety of concrete products and requirements for higher quality needs fast and accurate moisture measurement technology. In this paper fast accurate and material independent moisture measurement method is presented. Time domain reflectometry (TDR) sampling method for data acquisition has been used. In order to find the relationship between materials type and spectrum curve artificial neural network classifier (ANN) has been used. 5 mixtures from two materials (sand and crashed stone) in different proportions were correctly recognized using method proposed. Experiment confirmed ability to use TDR combined with ANN in material independent moisture measurement systems. Ill. 15, bibl. 9 (in English; summaries in English, Russian and Lithuanian).
