Design of variable stiffness fixture for computerized embroidery machine based on shape memory polymer

It is a challenge to handle the metal fixture used for cloth clamping in a computerized embroidery machine because of its fixed stiffness. Herein, a prototype that acts as a fixture to provide variable stiffness property is explored by discussing the potential of a thermal-sensitive epoxy resin-based shape memory polymer (SMP). The general model of fixture design is obtained after analyzing the working condition of the metal fixture. The structure of the SMP fixture is designed by discussing the material properties and working requirements of SMP, and a theoretical model is established to deduce the relationship between thickness and stiffness of the fixture. Six SMP fixtures that memorized clamping and opening state were manufactured with different proportions of raw materials. The results show that the designed fixtures have a lighter weight but higher clamping force than the metal fixture at room temperature (RT). It is the first work that demonstrates the potential of the SMP fixture to replace the metal fixture in the computerized embroidery machine and provides inspiration for product design with variable stiffness characteristic in engineering.

Optimization of a clamping concept based on machine learning

Fixtures are an important element of the manufacturing system, as they ensure productive and accurate machining of differently shaped workpieces. Regarding the fixture design or the layout of fixture elements, a high static and dynamic stiffness of fixtures is therefore required to ensure the defined position and orientation of workpieces under process loads, e.g. cutting forces. Nowadays, with the increase in computing performance and the development of new algorithms, machine learning (ML) offers an appropriate possibility to use regression methods for creating realistic, rapid and reliable equivalent ML models instead of simulations based on the finite element method (FEM). This research work introduces a novel method that allows an optimization of clamping concepts and fixture design by means of ML, in order to reduce manufacturing errors and to obtain an increased stiffness of fixtures and machining accuracy. This paper describes the preparation of a dataset for training ML models, the systematic selection of the most promising regression algorithm based on relevant criteria, the implementation of the chosen algorithm Extreme Gradient Boosting (XGBoost) and other comparable algorithms, the analysis of their regression results, and the validation of the optimization for a selected clamping concept.