Dynamic flexible job shop scheduling (DFJSS) is an important and complex combinatorial optimization problem. Heuristic methods have been extensively studied and proven to be effective in solving the job shop scheduling problems, but they still suffer from difficulties in real-time scheduling when dealing with dynamic environments. In comparison to heuristic methods, genetic programming hyper-heuristic (GPHH) is more suitable for tackling dynamic events since it can make real-time decisions by dispatching rules (DRs) automatically generated based on the current job shop state. However, most existing DR-based studies focus on time-related optimization objectives (e.g., makespan, tardiness, etc.), ignoring energy consumption, which is crucial for meeting the urgent needs of green manufacturing in current society. Therefore, this paper systematically designs the energy-efficient terminals for GPHH, following an in-depth analysis of energy flow in the job shop. Besides, the paper proposes the energy-efficient manually designed DRs based on the DR construction method. Experimental results demonstrate that the DRs containing the proposed energy-efficient terminals can effectively optimize energy-related objectives.

The measurement and monitoring of the dimensional characteristics of the body-in-white is an important part of the automobile manufacturing process. The process of using key point regression technology to perform online detection of complex features on body-in-white currently faces a bottleneck problem, namely limited training samples. Under the condition that the number of labeled normal map samples is limited, this paper proposes a framework for domain-independent self-supervised learning using a large number of original images. Under this framework, a self-supervised pre-order task is designed, which uses a large number of easily accessible unlabeled original images for characterization learning as well as a domain discriminator to conduct adversarial training on the feature extractor, so that the extracted representation is domain-independent. Finally, in the key point regression task of five different complex features, a series of comparative experiments were carried out between the method in this paper and benchmark methods such as supervised learning, conventional self-supervised learning, and domain-related self-supervised learning. The results show that the method proposed in this paper has achieved significant performance advantages. In the principal component analysis of extracting features, the representation extracted by the method in this paper does not show obvious domain information.