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.

Interactive Total Mixed Ration formulation using Differential evolution

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  2018 ASABE Annual International Meeting  1800196.(doi:10.13031/aim.201800196)
Authors:   Daniel D Uyeh, Rammohan Mallipeddi, Trinadh Pamulapati, Tusan Park, Junhee Kim, Seungmin Woo, Yushin Ha, Taehan Kim
Keywords:   Animal feed; Constraint; Differential evolution; Interactive; Optimization


Animal protein provides important sources of nutrients to humans worldwide. About 60 to 80% of production costs are incurred by animal feed which is dependent on the breed, class and phase of the animal. This is a non-deterministic polynomial-time hardness recurrent problem due to the existence of various constraints. Satisfying constraints at specific stages of breeding are often not possible for most programming tools as this entails the development of programs with intrinsic mechanisms to allow easing of constraints based on the necessities of users. Consequently, the formulation of the problems and systems of optimization should facilitate this. The conventional formulations were modified using tolerance parameters that enables constraints relaxation. A method of differential evolution, a variant of evolutionary algorithms with epsilon constraint handling is proposed. Results of our experimental trials indicated that easing requirements has direct connections with the cost and in some instances, quantity of feed. We propose a system which possesses the capability to explore for an optimal or best solution to satisfy the constraints and find the suitable components to be used in the formulation.

(Download PDF)    (Export to EndNotes)