Search results

The purpose of this paper is to design an automatic press-fit instrument to realize precision assembly and connection quality assessment of a small interference fitting parts, armature.

In this paper, an automatic press-fit instrument was developed for the technical problems of reliable clamping and positioning of the armature, automatic measurement and adjustment of the attitude and evaluation of the connection quality. To compensate for the installation error of the equipment, corresponding calibration method was proposed for each module of the instrument. Assembly strategies of axial displacement and perpendicularity were also proposed to ensure the assembly accuracy. A theoretical model was built to calculate the resistant force generated by the non-contact regions and then combined with the thick-walled cylinder theory to predict the press-fit curve.

The calibration method and assembly strategy proposed in this paper enable the press-fit instrument to achieve good alignment and assembly accuracy. A reasonable range of press-fit curve obtained from theoretical model can achieve the connection quality assessment.

This instrument has been used in an armature assembly project. The practical results show that this instrument can assemble the armature components with complex structures automatically, accurately, in high-efficiency and in high quality.

This paper provides a technical method to improve the assembly quality of small precision interference fitting parts and provides certain methodological guidelines for precision peg-in-hole assembly.

This study aims to summarize the critical issues in medical federated learning and applicable solutions. Also, detailed explanations of how federated learning techniques can be applied to the medical field are presented. About 80 reference studies described in the field were reviewed, and the federated learning framework currently being developed by the research team is provided. This paper will help researchers to build an actual medical federated learning environment.

Since machine learning techniques emerged, more efficient analysis was possible with a large amount of data. However, data regulations have been tightened worldwide, and the usage of centralized machine learning methods has become almost infeasible. Federated learning techniques have been introduced as a solution. Even with its powerful structural advantages, there still exist unsolved challenges in federated learning in a real medical data environment. This paper aims to summarize those by category and presents possible solutions.

This paper provides four critical categorized issues to be aware of when applying the federated learning technique to the actual medical data environment, then provides general guidelines for building a federated learning environment as a solution.

Existing studies have dealt with issues such as heterogeneity problems in the federated learning environment itself, but those were lacking on how these issues incur problems in actual working tasks. Therefore, this paper helps researchers understand the federated learning issues through examples of actual medical machine learning environments.