Optimization of an algae ball mill grinder using artificial neural network

• Main Authors: Fernando, Arvin H., Maglaya, Archie B., Ubando, Aristotle T.
• Format: text
• Published: Animo Repository 2017
• Subjects: Microalgae; Nannochloropsis; Neural networks (Computer science); Mechanical Engineering
• Online Access: https://animorepository.dlsu.edu.ph/faculty_research/1890; https://animorepository.dlsu.edu.ph/context/faculty_research/article/2889/type/native/viewcontent
• Institution: De La Salle University

Effects of the various ball mill operational grinding parameters for extracting microalgae were evaluated. This paper presents the use of MATLAB artificial neural network (ANN) for optimizing and improving the micro algae ball mill grinding process configuration set-up particularly on Nannochloropsis sp. The input parameters that was gathered, used and analyse are critical speed, duration, ball material, ball diameter, jar diameter, load percentage and ball-algae ratio. The researcher determines the amount of protein in the sample by using the Bradford Protein Assay Analysis. A total of 42 datasets was used to predict the optimize combination of the dataset. The authors used the MATLAB Programming and trained the neural network. MATLAB is used as an optimization tool to determine the best ball mill grinding configuration for the prototype set-up. © 2016 IEEE.