1 September 2018 in Applied Soft Computing
5 November 2022 in Applied Soft Computing
20 May 2020 in Grey Systems: Theory and Application
Purpose: The purpose of this paper is to propose an uncertainty representation and information measurement method for characterizing grey numbers, estimating their internal laws and solving how to generate them based on available information data in the real world.Design/methodology/approach: This paper attempts to present a new mathematical methodology in the field of grey numbers. The generalized grey number is defined at first with the concept of information elements and information samples. Then, the probability function of a grey number is proposed to describe the internal law of the grey number. By finding the feasible information elements from information samples, the probability calculation method for the true value of a grey number is presented. Finally, some numerical examples and comparisons are carried out to assess the efficiency and performance.Findings: The results show that the uncertainty representation and information measurement method is effective in characterizing and quantifying grey numbers based on available information data.Practical implications: Uncertain information is widespread in practical applications. In this manuscript, the grey number is represented and its information is measured through some existing data in discrete or interval forms, which provides a grey information concept that utilizes information elements to represent uncertainty in the real world.Originality/value: The proposal presents a novel data-driven method to generate a grey number representation from available data rather than the classical whitening weight function constructed from experience, and the dynamic evolution process of a grey number is measured by the increase of information samples.
20 January 2025 in IEEE Transactions on Evolutionary Computation
Integrated Order Batching and Picker Routing (IOBPR) is a complex combinatorial optimization problem in real-world intelligent manufacturing systems. Heuristics are often used for solving such complex scheduling problems. Manually designing scheduling heuristics suffer from two limitations: few problem features can be taken into account and the design process is time consuming. Genetic Programming Hyper Heuristic (GPHH) approaches have been proposed on many scheduling problems to automatically evolve effective heuristics. However, existing GPHH approaches are often problem specific and requires careful design of problem specific terminal sets and evolution operators. The aim of this work is to develop a GPHH approach to evolve heuristics for the IOBPR problem. In particular, we propose a novel terminal set (NT) with three types of terminals, and a GPHH with elitist mutation (GPHH-EM) algorithm. Extensive experiments demonstrate that the heuristics evolved by GPHH-EM can significantly outperform other state-of-the-art competing algorithms designed by human experts. Further analysis indicates that the three types of terminals effectively complement to improve evolved heuristics for decision making. Furthermore, the newly developed elitist mutation operator expedites the evolutionary process for GPHH to find high-quality heuristics.
5 January 2025 in Applied Soft Computing
8 April 2026 in Grey Systems: Theory and Application
Purpose: This study addresses a dual-resource constrained flexible job shop scheduling problem (DRCFJSP) in the context of Industry 5.0, where both machines and workers must be coordinated. It incorporates a team-based collaborative learning effect that dynamically enhances worker proficiencies and uses interval grey numbers to represent uncertain processing times. The aim is to optimize makespan, maximum team workload, and total worker proficiency improvement simultaneously. Design/methodology/approach: A multi-objective grey dual-resource constrained flexible job shop model is proposed, integrating interval grey numbers to represent uncertainties and a collaborative learning effect to reflect skill evolution. To solve this problem, a knowledge-guided multi-objective evolutionary algorithm (KGMOEA) is designed, featuring a four-layer encoding scheme and domain-specific strategies such as knowledge-guided population initialization and neighborhood search. Findings: The proposed algorithm outperforms benchmark methods in convergence and diversity. Incorporating collaborative learning effects reduces total completion time and improves resource allocation efficiency. Experimental results confirm that the method effectively balances production efficiency with workforce skill development under uncertainty. Practical implications: This paper provides a practical scheduling framework for high-complexity manufacturing environments, such as aviation composite workshops, where human–machine collaboration and skill development are critical. The proposed approach helps to optimize both production efficiency and worker proficiency growth under uncertain conditions, supporting resilient and sustainable manufacturing in the industry 5.0 era. Originality/value: This paper is the first work to integrate collaborative learning effects and interval grey numbers into the DRCFJSP, addressing both dynamic skill evolution and production uncertainties simultaneously. The work contributes to the shift from machine-centered to human–machine collaborative scheduling and provides a new model and algorithm for learning-oriented scheduling in uncertain environments.