Smart packing simulator for 3D packing problem using genetic algorithm

Abstract

Every year, at least 100 million tons of solid waste globally comes from packaging waste, in which partly created by inefficient packaging. Multiple box arrangement or bin packing solution directly addresses this problem which also affects storing space in production, manufacturing and logistics sector. Smart packing algorithm is designed for solving three-dimensional bin/container packing problem (3DBPP) which has numerous practical applications in various fields including container ship loading, pallet loading, plane cargo, warehouse management and parcel packing. This project investigates the implementation of genetic algorithm (GA) for a smart packing simulator in solving the 3DBPP applications. The smart packing system has an adaptable chromosome length GA for more robust implementation, where chromosome length will be changing with number of boxes. It can optimize multiple box arrangements and the boxes movements and positions are simulated through each GA generations, for realistic adaptation. The system is able to make optimum arrangement for the boxes so they can fit into a smallest container possible. The time taken for GA to converge varies with number of boxes.