Integration of artificial neural network with genetic algorithm for an optimum performance of a Chironji (Buchanania lanzan) nut decorticator
by Dileswar Pradhan; Rama Chandra Pradhan
International Journal of Postharvest Technology and Innovation (IJPTI), Vol. 7, No. 2, 2020

Abstract: This study has explored the integrated artificial neural network - genetic algorithm (ANN-GA) technique for the optimum performance of a Chironji (Buchanania lanzan) nut decorticator. To have desired outcomes, the performance of the decorticator was evaluated at 54 different combinations of independent variables. Those variables are six levels of moisture content of the nuts (3%, 6%, 9%, 12%, 15%, and 18% d.b.), three levels of the roller speed (400, 450, and 500 rpm), and three levels of clearance between the roller and plate (6.44, 6.95, and 7.46 mm). The optimum values found were the moisture content of 12.06% (d.b.), speed of 413 rpm, and clearance of 6.64 mm. With the optimised values, 14.69% of whole kernels, 3.45% of broken kernels, and 5.20% of un-decorticated nuts were recovered. A decorticating efficiency of 94.8% and a machine efficiency of 76.77% was recorded when the decorticator was operated at optimum conditions. The outcomes of this study will be useful for nut processing and elsewhere.

Online publication date: Thu, 17-Sep-2020

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Postharvest Technology and Innovation (IJPTI):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com