Pareto optimal design of reconfigurable rice seedling transplanting mechanisms using multi-objective genetic algorithm

• Published in: Neural computing & applications Vol. 27; no. 7; pp. 1907 - 1916
• Main Authors: Felezi, M. E., Vahabi, S., Nariman-zadeh, N.
• Format: Journal Article
• Language: English
• Published: London Springer London 01.10.2016; Springer Nature B.V
• Subjects: Artificial Intelligence; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Configuration management; Data Mining and Knowledge Discovery; Design optimization; Genetic algorithms; Image Processing and Computer Vision; Multiple objective analysis; Original Article; Planting; Probability and Statistics in Computer Science; Reconfiguration; Rice; Tracking errors; Transplantation; Pareto; Genetic algorithm; Optimization; Transplanting machine; Four-bar mechanism
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-015-1982-0

In this paper, an optimal reconfigurable four-bar linkage for a rice seedling transplanting machine is synthesized by a multi-objective uniform-diversity genetic algorithm. The design procedure has consisted of two stages. At the first stage of the design, a multi-objective synthesis of a four-bar linkage as a rice seedling transplant mechanism is accomplished considering two important objective functions of tracking error of an efficient path for planting of rice seedling and transmission angle’s deviation from 90° of transplant mechanism. At the second stage of the design, a further single-objective optimization is performed to refine the selected design from the first stage so that a reconfigurable four-bar linkage can be constructed for efficient and optimum operation condition as a seedling transplantation machine. Consequently, some practical curves for optimum design configuration of the mechanism are presented meeting the different specifications of both depth of seedling planting and forward velocity of the transplanter.