Multi-Strategy Discrete Teaching–Learning-Based Optimization Algorithm to Solve No-Wait Flow-Shop-Scheduling Problem

Abstract

To address the problems of the single evolutionary approach, decreasing diversity, inhomogeneity, and meaningfulness in the destruction process when the teaching–learning-based optimization (TLBO) algorithm solves the no-wait flow-shop-scheduling problem, the multi-strategy discrete teaching–learning-based optimization algorithm (MSDTLBO) is introduced. Considering the differences between individuals, the algorithm is redefined from the student’s point of view, giving the basic integer sequence encoding. To address the fact that the algorithm is prone to falling into local optimum and to leading to a reduction in search accuracy, the population was divided into three groups according to the learning ability of the individuals, and different teaching strategies were adopted to achieve the effect of teaching according to their needs. To improve the destruction-and-reconstruction process with symmetry, an iterative greedy algorithm of destruction–reconstruction was used as the main body, and a knowledge base was used to control the number of meaningless artifacts to be destroyed and to dynamically change the artifact-selection method in the destruction process. Finally, the algorithm was applied to the no-wait flow-shop-scheduling problem (NWFSP) to test its practical application value. After comparing twenty-one benchmark test functions with six algorithms, the experimental results showed that the algorithm has a certain effectiveness in solving NWFSP.