A Sequence Fine-Tuning Strategy Based Evolutionary Algorithm for Solving Project Scheduling Problems

As artificial intelligence technology advances, the industrial landscape has been gradually transitioning from man-ual labor to automated manufacturing processes. This shift has highlighted the growing tension between production scheduling efficiency and cost considerations, culminating in the emergence of Project Scheduling Problems (PSP). Since the emergence of this problem, there have been many ways to deal with this kind of problems, but most of the existing algorithms cannot be used in production problems, and thus cannot provide enterprises with more considerable benefits and costs. Therefore, this paper takes datasets from an actual production enterprise and solves the corresponding PSP problems, by means of designing a multi-objective optimization algorithm based on the characteristics of the PSP problems. Based on a sequence encoding, the proposed algorithm designs a repair strategy for decision variables ac-cording to various constraints of the PSP problems, and adds a sequence fine-tuning strategy based on sequence constraints, ensuring the diversity of solutions and improving the feasibility and stability of understanding. We perform experiments and analysis on several datasets involving 138 to 1 380 decision variables, and the results show that the proposed algorithm is more effective than several existing multi-objective evolutionary algorithms.