ABSTRACT
Additive manufacturing (AM) technologies are growing more and more in the manufacturing industry;the increase in world energy consumption encourages the quantification and optimization of energy use in additive manufacturing processes. Orientation of the part to be printed is very important for reducing energy consumption. Our work focuses on defining the most appropriate direction for minimizing energy consumption. In this paper, twelve machine learning (ML) algorithms are applied to model energy consumption in the fused deposition modelling (FDM) process using a database of the FDM 3D printing of isovolumetric mechanical components. The adequate predicted model was selected using four performance criteria: mean absolute error (MAE), root mean squared error (RMSE), R-squared (R2), and explained variance score (EVS). It was clearly seen that the Gaussian process regressor (GPR) model estimates the energy consumption in FDM process with high accuracy: R2 > 99%, EVS > 99%, MAE < 3.89, and RMSE < 5.8.
ABSTRACT
As the epidemic situation became more widespread in the wake of the Covid-19 pandemic, the economic impact on a wide variety of industries began to grow steadily. One sector particularly affected by this issue is the automotive indus-try, which relies on a smooth supply chain largely because of the large number of electrical and mechanical components. One of these components are so-called semiconductors. The following article presents an analysis of the semiconductor shortage in the automotive industry in the context of risk and crisis management and derives recommendations for action. In addition to outlining the causes, the article focuses primarily on the question of how solution strategies for preventing a global semiconductor shortage could look in the future. The central question for this consideration is: could the current situation have been prevented by more effective risk and crisis management?. © 2022 Walter de Gruyter GmbH, Berlin/Boston, Germany.
ABSTRACT
This paper presents the Smart Covid-Assist Bot using Image Processing which is an embedded IoT (Internet of Things) based project consisting of electronic and mechanical components. The Covid-Assist Bot consists of many features and can create a huge impact on the spread of this pandemic. It can monitor and store the temperature details in the database and can also be used to sanitize the entire surface using UVC and disinfectants. All the data from the sensors can be stored and used later. The cost of the bot is very low and has more features when compared with the robots and products available in the market. The accuracy is also high and compactable. The physical structure of the Covid-Assist bot has been drawn using the TinkerCad software. This paper covers the working principle, material and method used, circuit diagram and model structure. © 2021 IEEE.
ABSTRACT
In the last few decades, robots have fostered unique possibilities for musical performance and composition, allowing novel interactions with musicians and memorable experiences for the audience. Robotic musicians can be built in many shapes and have diverse functionalities, making robot musicianship a fertile research field. However, building physical robots requires access to electrical and mechanical components, as well as laboratory equipment, which can make them financially unfeasible in peripheral countries. Moreover, building physical experimental devices quickly raises the problem of disposing of broken or outdated parts. Finally, the COVID-19 crisis has decreased access to laboratories and forced social isolation, which further harms physical robots’ development. In this position paper, we argue that the current technology for robot simulation can be used to provide most aspects of physical robots, with considerable advantages related to the financial cost, the environmental impact, and the possibility of testing and sharing robots using the Internet. We also discuss previous work on virtual presence, which indicates that both the performers and the audience can feel being present in the same space as the virtual robots. Lastly, we anticipate challenges and research opportunities in this field of research. Copyright: © 2021 the Authors.