Zahra Kalantar - Faculty of Chemistry, Shahrood University of Technology, Shahrood, Iran
Najmeh Khatoon Namjoo - Faculty of Chemistry, Shahrood University of Technology, Shahrood, Iran

Ketones belong to a class of organic compounds known as carbonyls in which a carbon atom linked to an oxygen atom with a double bond (C=O). As solvents, ketones have the ability to dissolve other materials or substances, particularly polymers and adhesives. Theyare ingredients in epoxies, polyurethane, degreasers, and cleaningsolvents. Ketones are also used in industry for the manufacture ofplastics and composites and in pharmaceutical and photographic filmmanufacturing. Because they have high evaporation rates and dryquickly, they are sometimes employed in drying applications.Because of wide usage of ketones in different chemical industries,the knowledge of the thermodynamic properties of ketones and theirdependencies to temperature and pressure is a prerequisite forsynthesis and design of chemical process. However, it is not alwayspossible to find experimental values of the properties for the compounds of interest in the literature. Therefore, estimation methods are generally employed in this situation. In recent years artificial neural networks (ANN) an combination of wavelet theory with neural networks, namely wavelet neural network (WNN), have provided a high performance nonlinear analysis tool that may be used to avoid the shortcomings involved in prediction methods [1,2]. Hence, in this work we used WNN for density prediction of ketones over a wide range of temperature and pressure.