Self-Adaptive Genetic Algorithm For Bucket Wheel Reclaimer Real-Parameter Optimization

Abstract

Bucket wheel reclaimer (BWR) is a complex engineering machine widely used in the open pit mine; it is characterized by the low efficiency and high maintenance cost. The boom, namely a typical framework structure, is a core component of BWR, which affects the performance of the BWR directly. For addressing this issue, this paper proposes a self-adaptive genetic algorithm (AGA) to improve the performance of the genetic algorithm (GA). The standard genetic algorithm has been improved to enhance the optimization efficiency, because the optimization problem is believed to be highly non-linear. The AGA has been verified by two framework structures, and the results of AGA are compared with the corresponding results of previous literature. Furthermore, the AGA is applied to obtain the optimal size and shape of the BWR boom by taking the BWR boom as a space framework structure, and improve BWR's performance by meeting the requirements of the intensity and rigidity. The results show that the improved genetic algorithm has a higher efficiency than the standard GA. The structure optimization of the BWR boom is performed using the AGA. From the optimization, BWR boom's weight decreases by 23.46% from the initial weight.

Keywords

• Bucket wheel reclaimer
• framework structure
• improved genetic algorithm
• structural shape optimization