Search

In the field of industrial inspection, accurate detection of thread quality is crucial for ensuring mechanical performance. Existing machine-vision-based methods for internal thread defect detection often face challenges in efficient detection and sufficient model training samples due to the influence of mechanical geometric features. This paper introduces a novel image acquisition structure, proposes a data augmentation algorithm based on Generative Adversarial Networks (GANs) to effectively construct high-quality training sets, and employs a YOLO algorithm to achieve internal thread defect detection. Through multi-metric evaluation and comparison with external threads, high-similarity internal thread image generation is achieved. The detection accuracy for internal and external threads reached 94.27% and 93.92%, respectively, effectively detecting internal thread defects. [ABSTRACT FROM AUTHOR]

The meta-learning method proposed in this paper addresses the issue of small-sample regression in the application of engineering data analysis, which is a highly promising direction for research. By integrating traditional regression models with optimization-based data augmentation from meta-learning, the proposed deep neural network demonstrates excellent performance in optimizing glass fiber reinforced plastic (GFRP) for wrapping concrete short columns. When compared with traditional regression models, such as Support Vector Regression (SVR), Gaussian Process Regression (GPR), and Radial Basis Function Neural Networks (RBFNN), the meta-learning method proposed here performs better in modeling small data samples. The success of this approach illustrates the potential of deep learning in dealing with limited amounts of data, offering new opportunities in the field of material data analysis. [ABSTRACT FROM AUTHOR]

There is an error in affiliation 1 for author Gengpei Zhang. Affiliation 1 should be: School of Electronic Information and Electrical Engineering, Yangtze University, Jingzhou City, Hubei Province, ChinaBy Gengpei Zhang and Xiongding LiuReported by Author; Author [Extracted from the article]

Although surface topography is a directive and useful method to evaluate the quality of worn components, the common belief that the surface roughness after running-in is independent of the nature of initial roughness makes it difficult to investigate the surface topography of worn components after running-in based on unworn surface before running-in process. Trying to build the connection of surface topography before and after running-in, this article assumed running-in as a black box and adopted support vector machine as machine learning method to simulate the complex process. Through the training and validation of the simulation, the predictive model of surface topography after running-in based on unworn surface topography was established, which indicated the existence of a correlation between the surface topographies before and after running-in. The model analysis revealed that the hybrid properties of surface topographies before and after running-in have strong correlation. Especially, the correlation between input parameter Sk and output parameter Sq is a particular one among all relationships of parameter pairs. [ABSTRACT FROM PUBLISHER]