The flexible job shop scheduling problem with limited automatic guided vehicles (FJSP-AGV) is prevalent in manufacturing enterprises. To improve production efficiency and reduce energy consumption, this paper investigates the energy-efficient FJSP-AGV (EFJSP-AGV), aiming to minimize both the makespan and total energy consumption. To address EFJSP-AGV, both exact and approximate methods were developed. The exact method employs a novel mixed integer linear programming (MILP) model, capable of producing optimal Pareto solutions for small-sized instances using the epsilon method. EFJSP-AGV is an NP-hard problem that involves three subproblems: operation sequencing, machine selection, and AGV selection. To overcome these challenges, a novel approximate method called imitation learning (IL)-assisted multi-population evolutionary algorithm (ILMPEA) was proposed. The multi-population evolutionary framework assigns distinct search regions to populations to improve the efficiency of solution space exploration. To further enhance search accuracy, IL is applied to select search operators, guiding the Pareto front toward a better approximation of the true front. Experimental results demonstrated the effectiveness of both the MILP model and ILMPEA.

This article studies the flexible job shop scheduling problem with a certain number of automatic guided vehicles (FJSP-AGVs), aiming to minimize the makespan. First, a novel constraint programming (CP) model is formulated to obtain optimal solutions. Specifically, the proposed CP model addresses the shortcomings of the existing CP model, which cannot solve instances with a machine processing two consecutive operations of the same job. Additionally, redundant and symmetry-breaking constraints are designed to accelerate constraint propagation and break problem symmetry, respectively. Then, to more effectively solve FJSP-AGVs, a CP-assisted meta-heuristic algorithm framework is designed, with a CP-assisted dual-population collaborative genetic algorithm (DCGA-CP) being developed as an example. Finally, experiments are performed on benchmark instances to demonstrate the effectiveness and superiority of the proposed CP model and DCGA-CP. Experimental results show that the proposed CP models first prove 29 new optimal solutions and improve 27 best-known solutions. Meanwhile, DCGA-CP first proves 29 new optimal solutions and improves 32 best-known solutions for benchmark instances.

Disassembly is the first phase to demanufacture end-of-life (EOL) products that are separated into parts/components for recovery. The quality conditions of EOL products are highly uncertain, which would result in some uncertain information during the disassembly process, e.g., the disassembly time and recovering revenue of each subassembly. It is quite challenging to determine the optimal/near-optimal disassembly solutions under uncertain information. This article studies uncertain disassembly planning (UDP) and proposes a self-adaptive learning approach to quickly identify the near-optimal disassembly solutions. First, we model the UDP by extending Petri nets, where not only disassembly operations but also EOL options of each subassembly are represented in the extended Petri Net. Based on the UDP model, we develop the self-adaptive learning approach, which integrates an approximation procedure for estimating uncertain disassembly information, aQ-learning algorithm for training disassembly samples, and a heuristic method for selecting the best disassembly solution. Finally, a hybrid Li-ion battery pack of Audi A3 Sportback e-tron is selected as the case study and applied to test the proposed self-adaptive learning approach. The experimental results demonstrate that our proposed method can efficiently find a better disassembly solution than the existing disassembly solution within 200 trainings in the case study.

Demanufacturing aims to recover value and conserve energy from end-of-life (EOL) products, contributing to sustainable manufacturing. To make the full use of EOL products, they are usually disassembled into components that have different values and embodied energy at different EOL options. This article studies a disassembly planning (DP) that integrates the decisions on disassembly sequence and EOL strategy to maximize the recovered value and energy conservation from EOL products. We propose a multiobjective DP based on the value recovery and energy conservation (MDPVE) model, which is different from the existing DP models by focusing on the embodied energy rather than the energy consumption during disassembly. An adapted multiobjective artificial bee colony (ABC) algorithm [multiobjective ABC (MOABC)] is developed to identify the Pareto solutions for the MDPVE and is compared with a well-known metaheuristic algorithm, Non-dominated Sorting Genetic Algorithm-II (NSGA-II). A real-world case study demonstrated the superior solution quality and computational efficiency of MOABC. Note to Practitioners-There is often more than one treatment option for EOL products or components, including reuse, remanufacturing, and recycling. However, the decision on which EOL option to select is not considered in most of the DP studies by assuming an EOL option given for each component. Hence, the disassembly plan with the EOL decision is focused in this article. As energy sustainability gains an increasing attention, it is essential to assess the profitability and energy conservation simultaneously for EOL products. Since there could be a tradeoff between recovered profit and conserved energy, a multiobjective evolutionary algorithm is developed for generating Pareto solutions which help decision-makers to find good solutions for both evaluation indicators.

Smart shared mobility is an emerging transportation strategy that promotes sustainable and intelligent transportation. Bike sharing is one mode of smart shared mobility and is gaining popularity in recent years. To ensure a smooth operation of a bike sharing system (BSS), it is essential to redistribute the bicycles, which includes picking up returned bicycles and relocating them to best serve customers. A bike sharing rebalancing problem (BSRP) has thus emerged. This paper addresses a static BSRP which operates during the night when shared bikes are rarely utilized or when the BSS is closed. We studied a single-vehicle BSRP (sBSRP) and multi-vehicle BSRP (mBSRP) with the objective of minimizing the depot inventory cost as well as the traveling cost. For mBSRP, six formulations are presented i.e. five mixed integer programming models (mBSRP1-mBSRP5) and a mixed integer linear programming model (mBSRP6). In addition, an iterative procedure combined with the branch-and-cut algorithm in the CPLEX solver is developed to solve this problem. A real-world case study is employed to test the effectiveness of the formulations, and a set of benchmark instances are adopted to further compare the performances of mBSRP5 and mBSRP6. The experimental results show that mBSRP6 performs the best among the six models, offering the best solution quality and computational efficiency. Finally, mBSRP6 is applied to determine the depot inventory for the case study using random demand datasets.

Due to the rapid technology advancement and market changes, products are becoming outdated and subsequently discarded faster than ever before. Recovery, recycling, and remanufacturing of end-of-life (EOL) products are getting more attention. Disassembly is indispensable to recycle and remanufacture EOL products, and a disassembly line is an efficient way to perform it. A disassembly line balancing problem (DLBP) aims at streamlining the disassembly activities such that the total disassembly time consumed at each workstation is approximately the same and approaching the cycle time. However, the assignment of disassembly operations to workstations in a disassembly shop should ensure the recovery of valuable components and reduce undesirable impact on the environment as much as possible. In this paper, a novel heuristic technique combining multicriterion decision making (MCDM) and general variable neighborhood search (GVNS) is proposed to solve the DLBP. Based on the characteristics of the DLBP, an innovative MCDM method based on fuzzy set theory, grey relational analysis, and Choquet fuzzy integral is developed to evaluate the performance scores and determine the ranking of disassembly tasks. Subsequently, an improved GVNS algorithm is employed to further balance a disassembly line with three objectives, in which a new metric is formulated to integrate with the ranking from MCDM. The proposed method not only takes a comprehensive objective system into consideration but effectively generates a good enough tradeoff disassembly solution. Finally, the proposed approach is illustrated with an example and compared with two other heuristics to show its efficacy in solving the DLBP.

This paper investigates an energy-efficient hybrid flowshop scheduling problem with the consideration of machines with different energy usage ratios, sequence-dependent setups, and machine-to-machine transportation operations. To minimize the makespan and total energy consumption simultaneously, a mixed-integer linear programming (MILP) model is developed. To solve this problem, a three-stage multiobjective approach based on decomposition (TMOA/D) is suggested, in which each solution is bound with a main weight vector and a set of its neighbors. Accordingly, a variable direction strategy is developed to ensure each solution along its main direction is thoroughly exploited and can jump to the neighboring directions using a proximity principle. To ensure an active schedule of arranging jobs to machines, a two-level solution representation is employed. In the first phase, each solution attempts to improve itself along its current weight vector through a developed neighborhood-based local search. In the second phase, the promising solutions are selected through the technique for order preference by similarity to an ideal solution. Then, they attempt to update themselves with a proposed global replacement strategy via incorporation with their closing solutions. In the third phase, a solution conducts a large perturbation when it goes through all its assigned weight vectors. Extensive experiments are conducted to test the performance of TMOA/D, and the results demonstrate that TMOA/D has a very competitive performance.