Galactic Swarm Optimization (GSO) is an optimization method inspired by the movements of stars and star clusters in the galaxy. This method aims to find the best solution in two phases using other known optimization methods. The first phase explores the search space, while the second phase tries to refine the best solution. In GSO, the population of the best individuals obtained from the first phase is used as the initial population for the second phase. This process is repeated until the stopping criterion is met. Although the knowledge obtained from the first phase is transferred to the second phase in GSO, there is no knowledge transfer from the second phase to the first phase. In this study, we propose a modification where the knowledge obtained in the second phase is transferred back to the first phase. Additionally, the Particle Swarm Optimization (PSO) method, used as the search method in the original study, has a fast convergence problem, which hinders an effective discovery process in the first phase of GSO. To address this, the proposed diversity-guided modification regulates population diversity and enhances exploration. To demonstrate the performance of the proposed method, twenty-six traditional benchmark functions and three engineering design problems were used. The proposed method was compared with the original GSO and six current optimization methods. The results of the experimental study were analyzed using statistical tests. The experimental results and analyses show that the proposed method performs successfully.
In industrial production processes, accurate and fast detection of band sawtooth deformations is of critical importance. Traditional detection approaches are not sustainable at industrial scale due to their high human attention requirements and low efficiency. In this study, we present RTC-DETR234, a task-specific configuration of the RT-DETR architecture designed for detecting small and low-contrast band sawtooth fractures. The proposed model uses the P2–P4 scales to provide higher-resolution feature extraction instead of the P3–P5 scaling structure of the baseline RT-DETR model. Furthermore, CBAM modules are integrated into the HGBlock-based backbone to refine channel- and spatial-level feature responses associated with small and low-contrast fracture regions. The proposed model, the baseline YOLO models, and the baseline RT-DETR model are trained and compared on a dataset consisting of band sawtooth defects. The proposed model achieved an average mAP of 0.9938 for tooth detection and 0.9178 for fracture detection across multiple independent runs.