With the rapid development of Industrial 4.0, the modern manufacturing system has been experiencing profoundly digital transformation. The development of new technologies helps to improve the efficiency of production and the quality of products. However, for the increasingly complex production systems, operational decision making encounters more challenges in terms of having sustainable manufacturing to satisfy customers and markets’ rapidly changing demands. Nowadays, rule-based heuristic approaches are widely used for scheduling management in production systems, which, however, significantly depends on the expert domain knowledge. In this way, the efficiency of decision making could not be guaranteed nor meet the dynamic scheduling requirement in the job-shop manufacturing environment. In this study, we propose using deep reinforcement learning (DRL) methods to tackle the dynamic scheduling problem in the job-shop manufacturing system with unexpected machine failure. The proximal policy optimization (PPO) algorithm was used in the DRL framework to accelerate the learning process and improve performance. The proposed method was testified within a real-world dynamic production environment, and it performs better compared with the state-of-the-art methods.

Remanufacturing prolongs the life cycle and increases the residual value of various end-of-life (EoL) products. As an inevitable process in remanufacturing, disassembly plays an essential role in retrieving the high-value and useable components of EoL products. To disassemble massive quantities and multi-types of EoL products, disassembly lines are introduced to improve the cost-effectiveness and efficiency of the disassembly processes. In this context, disassembly line balancing problem (DLBP) becomes a critical challenge that determines the overall performance of disassembly lines. Currently, the DLBP is mostly studied in straight disassembly lines using single-objective optimization methods, which cannot represent the actual disassembly environment. Therefore, in this paper, we extend the mathematical model of the basic DLBP to stochastic parallel complete disassembly line balancing problem (DLBP-SP). A novel simulated annealing-based hyper-heuristic algorithm (HH) is proposed for multi-objective optimization of the DLBP-SP, considering the number of workstations, working load index, and profits. The feasibility, superiority, stability, and robustness of the proposed HH algorithm are validated through computational experiments, including a set of comparison experiments and a case study of gearboxes disassembly. To the best of our knowledge, this research is the first to introduce gearboxes as a case study in DLBP which enriches the research on disassembly of industrial equipment.

The disassembly line of remanufacturing has significance economic and social value for dealing with the massive increasing number of disposal products. As the typical multi-objective optimization (MOO) problem, the disassembly line balancing problem (DLBP) is one of typical NP-hard problem which has the characteristic of high computational complexity. There has no summarize of MOO algorithms for the remanufacturing DLBP. Therefore, this paper main reviewed three main categories of the optimization algorithms for remanufacturing DLBP and comparing the advantages and disadvantages of various algorithms. Additionally, identify the challenges and future research directions of remanufacturing DLBP.

Current wind turbine blade inspection practices rely heavily on inefficient manual review, while automated deep learning models struggle to balance real-time deployment constraints with detection accuracy under complex background interference. To bridge this gap, this paper proposes the Lightweight Hypergraph Computation and Information-Aware Defect Detection Network (LHCI-Net), a novel architecture engineered to achieve an optimal trade-off between precision and computational efficiency. The proposed method introduces a custom lightweight backbone to drastically reduce computational overhead, an information-aware feature interaction module to actively suppress background noise using polarity and frequency-domain perception, and a hypergraph computation feature aggregation module to establish deep, high-order connections between features. The model is optimised for edge deployment using targeted pruning and knowledge distillation techniques. Experimental results on a custom wind turbine blade image dataset and an open-source DTU dataset validate LHCI-Net's superiority. Compared to state-of-the-art models like YOLOv8, YOLOv11, YOLO26, and RT-DETR, LHCI-Net improves mean Average Precision (mAP) by up to 4.53%, while simultaneously reducing computational load by up to 47.0G Floating Point Operations (FLOPs), demonstrating its exceptional robustness and suitability for practical, real-world wind turbine blade inspections.