Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

This paper studies a neural network model of tea quality evaluation based on the chemical compositions such as fiber, nitrogen, infused contents and water. Function Link Network (FLN), which is a kind of forward neural network consisting of two layers, is adopted in this research. The preprocessing of data, the construction of neural network for tea quality evaluation and the training of the network are discussed. The result of an experiment shows that applying FLN in tea quality evaluation is better than using multiplelinear regression.