Search

This study identified the competency requirement for artificial intelligence in finite element analysis. The 10 Delphi group members included 5 field engineers in mechanical fields and 5 scholars from a technology institute. Next, 10 field experts were invited to participate. Using the Delphi technique and analytic hierarchy process, questionnaires were designed to assess competency indicators of artificial intelligence in finite element analysis. The data collected from questionnaires were analyzed using a nonparametric Wilcoxon signed-rank test, the Z value of the Kolmogorov-Smirnovone (KS) test, and relative weight. To fulfill the research objectives, a questionnaire was designed to collect data for 40 general competencies in 10 domains: (1) introduction to the finite element method, (2) pretreatment, (3) coordinate system, (4) model construction skills, (5) boundary conditions and solutions, (6) post processor application, (7) machine learning, (8) neural network, (9) deep learning, and (10) artificial intelligence in finite element analysis. The results of the three rounds of the Delphi technique expert questionnaire revealed essential professional competencies for AI in FEA. These findings can be used to devise a training and development plan and provide valuable references for educators in the field of engineering and technical education.

This paper investigates the optimization of tensile strength, tensile strength per unit weight, and tensile strength per unit time of polyethylene terephthalate glycol (PETG) material in fused deposition modeling (FDM) technology using the Taguchi method and analysis of variance (ANOVA). Unlike previous studies that typically focused on optimizing a single mechanical property, our research offers a multi-dimensional evaluation by simultaneously optimizing three critical quality characteristics: tensile strength, tensile strength per unit weight, and tensile strength per unit time. This comprehensive approach provides a broader perspective on both the mechanical performance and production efficiency, contributing new insights into the optimization of PETG in FDM. The Taguchi method ( L 16   4 5 ) was designed and executed, with the layer height, infill density, print temperature, print speed, and infill line direction as the control factors. Sixteen tensile tests were conducted, and ANOVA was employed to identify the main influencing factors for each quality characteristic. For the tensile strength, the infill density was found to have the greatest impact (48.45%), while the print temperature had the least impact (0.78%). The optimal parameter combination reduced the quality loss to 31.28% and standard deviation to 55.93%. For tensile strength per unit weight, the infill line direction had the greatest impact (87.22%), whereas the print temperature had the least impact (0.77%). The optimal parameter combination reduced the quality loss to 54.09% and standard deviation to 73.54%. Regarding the tensile strength per unit time, the layer height had the greatest impact (82.12%), while the print temperature had the least impact (0.08%). The optimal parameter combination reduced the quality loss to 10.81% and standard deviation to 32.87%. [ABSTRACT FROM AUTHOR]

In recent years, additive manufacturing has been widely used in industrial, medical, and educational fields. Material extrusion is used in most industries to increase development efficiency and reduce costs. This study used the material extrusion to discuss the print quality of additive manufacturing and optimized the processing parameters based on material properties. Based on the literature, this study summarized the fishbone diagram influencing printing quality. The layer height, nozzle temperature, printing speed, infill pattern, and filling spacing were selected as the control factors of the Taguchi method. An orthogonal array L16 was used for parameter design. The optimal parameters were analyzed using the variance and the response surface method. The results of the study are as follows. [ABSTRACT FROM AUTHOR]

In the industrial era, production equipment serves as an essential mother machine. In the global manufacturing industry, components such as laptop computers, mobile phones, and automotive parts all strive for aesthetic appearance. Taiwan's machine tool industry plays a significant role globally. Faced with the constantly changing market environment, the development and competitive advantage of CNC machines are crucial topics for manufacturers. Domestic manufacturers of computer numerical control machines should move towards the integration of automated equipment to accommodate various advanced parts processing procedures. Smart manufacturing will become the trend of the industry in the future. This study invited experts from academia, industry, and research institutions to conduct expert interviews. Their opinions were compiled and analyzed, supplemented by fuzzy Delphi analysis to establish the development trends of various modules. The feasibility and demand of the product's functional technology for industrial development were analyzed under three research dimensions and eight technical items. A total of 26 key sub-technical items were identified, achieving an expert consensus level of over 80. Furthermore, the importance ranking was analyzed using the fuzzy analytic hierarchy process, and the consistency tests were passed with C.I. < 0.1 and C.R. < 0.1. Finally, the obtained importance ranking of the hierarchical structure was used to predict the future development of computer numerical control machines through a technology roadmap, helping manufacturers use it as a reference model for future development trends to enhance market competitiveness. [ABSTRACT FROM AUTHOR]