Reinforcing the polymer with nanoparticles and fibers improves the mechanical, thermal and electrical properties. Owing to this, the functional parts produced by the FDM process of such materials can be used in industrial applications. However, optimal parameters’ selection is crucial to produce parts with optimal properties, such as mechanical strength. This paper focuses on the analysis of influential process parameters on the tensile strength of FDM printed parts. Two statistical methods, RSM and ANN, were applied to investigate the effect the layer thickness, printing speed, raster angle and wall thickness on the tensile strength of test specimens printed with a short carbon fiber reinforced polyamide composite. The reduced cubic model was developed by the RSM method, and the correlation between the input parameters and the output response was analyzed by ANOVA. The results show that the layer thickness and raster angle have the most significant influence on tensile strength. As for machine learning, among the nine different tested ANN topologies, the best configuration was found based on the lowest MAE and MSE test sample result. The results show that the proposed model could be a useful tool for predicting tensile strength. Its main advantage is the reduction in time needed for experiments with the LOSO (leave one subject out) k-fold cross validation scheme, offering better generalization ability, given the small set of learning examples.

For the designing of cutting-dies is a complex and experience-based process, it is poorly supported by conventional 3D CAD software. Thus, the majority of design activities, including the (re)modeling of those cutting die-components that are directly responsible for performing shaping operations on a sheet-metal stamping part, traditionally still need to be carried-out repetitively, separately, and manually by the designer. To eliminate some of these drawbacks and upgrade the capabilities of conventional 3D CAD software, this paper proposes a new methodology for the development of a parametric system capable of automatically performing a (re)modeling process of compound washer dies' cutting-components. The presented methodology integrates CATIA V5 built-in modules, including Part Design, Assembly Design and Knowledge Advisor, publication mechanism, and compound cutting die-design knowledge. The system developed by this methodology represents an 'intelligent' assembly template composed of two modules GAJA1 and GAJA2, respectively. GAJA1 is responsible for the direct input of the die-design problem regarding the shape, dimensions and material of the stamping part, its extraction in the form of geometric features, and the transferring of relevant design parameters and features to the module GAJA2. GAJA2 interprets the current values for the input parameters and automatically performs the modeling process of cutting die-components, using die-design knowledge and the company's internal design and manufacturing standards. Experimental results show that this system significantly shortens the modeling-time for cutting the die-components, improves the modeling-quality, and enables the training of inexperienced designers.

No abstract

This paper presents a knowledge-based system capable of giving the designer quality support when making decisions from the aspect of modeling the reinforcement of a plate-press within a position of maximum compressive load, and by choosing suitable material for the plate. Based on the selected combination of reinforcement and material, this system acquaints the user with the size and position of the largest comparative stress, and the greatest nodal displacement in the load-direction. This system operates based on the implemented knowledge of experts in the execution of design, material selection, and numerical analysis based on the finite-element method (FEM), which was written with the help of parameters within the knowledge-base of the CATIA V5 CAD-system. Using this system gives the user an opportunity to reach conclusions that are crucial for designing a plate-press or pressure-loaded die-elements, in general. The results reveal that the system can dramatically shorten design time and improve design quality in comparison to manual design process.

Designing of stamping dies is a complex procedure where comprehensive knowledge is needed, in order to understand the interactions of various interdependent parameters that are extensively engaged within all development phases of a sheet-metal stamping product. Many important die design decisions are made based on technological knowledge, which is especially closely related to understanding the activities of product design and process planning. Due to the lack of such valuable knowledge within conventional three-dimensional computer-aided design systems, a concurrent system for supporting technological aspect of die design process is proposed within this article. The system that was developed on top of computer-aided three-dimensional interactive application CATIA V5 product lifecycle management software enables die design automation on the basis of constraint solving. Product design and process planning activities are accomplished concurrently by system's modules. Finally, it extracts relevant technological information and decisions directly to the die design phase. The system also represents unique basis for the development of some modules capable of automatic reasoning, regarding die design and performing actions on this basis. The experimental results showed that the use of this system significantly shortens sheet-metal product development cycle, improves its quality, and enables efficient training of inexperienced designers.