The increasing availability of data, which becomes a continually increasing trend in multiple fields of application, has given machine learning approaches a renewed interest in recent years. Accordingly, manufacturing processes and sheet metal forming follow such directions, having in mind the efficiency and control of the many parameters involved, in processing and material characterization. In this article, two applications are considered to explore the capability of machine learning modeling through shallow artificial neural networks (ANN). One consists of developing an ANN to identify the constitutive model parameters of a material using the force–displacement curves obtained with a standard bending test. The second one concentrates on the springback problem in sheet metal press-brake air bending, with the objective of predicting the punch displacement required to attain a desired bending angle, including additional information of the springback angle. The required data for designing the ANN solutions are collected from numerical simulation using finite element methodology (FEM), which in turn was validated by experiments.

Press brake air bending, a process of obtaining products by sheet metal forming, can be considered at first sight a simple geometric problem. However the accuracy of the obtained geometries involves the combination of multiple parameters directly associated with the tools and the processing parameters, as well as with the sheet metal materials and dimensions. The main topic herein presented deals with the capability of predicting the punch displacement process parameter that enables the product to be accurately shaped to a desired bending angle, in press brake air bending. In our approach, it is considered separately the forming process and the elastic recovery (i.e. the springback effect). Current solutions in press brake numerical control (computer numerical control) are normally configured by analytical models developed from geometrical analysis and including correcting factors. In our approach, it is proposed to combine the use of a learning tool, artificial neural networks, with a simulation and data generation tool (finite element analysis). This combination enables modeling the complex nonlinear behavior of the forming process and springback effect, including the validation of results obtained. A developed model taking into account different process parameters and tool geometries allow extending the range of applications with practical interest in industry. The final solution is compatible with its incorporation in a computer numerical control press brake controller. It was concluded that, using this methodology, it is possible to predict efficient and accurate final geometries after bending, being also a step forward to a “first time right” solution. In addition, the developed models, methodologies and obtained results were validated by comparison with experimental tests.

The continuous evolution of metallic alloys in the automotive industry has led to the development of more advanced and flexible constitutive models that attempt to accurately describe the various fundamental properties and behavior of these materials. These models have become increasingly complex, incorporating a larger number of parameters that require an accurate calibration procedure to fit the constitutive parameters with experimental data. In this context, machine learning (ML) methodologies have the potential to advance material constitutive modeling, enhancing the efficiency of the material parameter calibration procedure. Recurrent neural networks (RNNs) stand out among various learning algorithms due to their ability to process sequential data and overcome limitations imposed by nonlinearities and multiple parameters involved in phenomenological models. This study explores the modeling capabilities of long short-term memory (LSTM) structures, a type of RNN, in predicting the hardening behavior of a sheet metal material using the results of a standardized experimental three-point bending test, with the aim of extending this methodology to other experimental tests and constitutive models. Additionally, a variable analysis is performed to select the most important variables for this experimental test and assess the influence of friction, material thickness, and elastic and plastic properties on the accuracy of predictions made by neural networks. The required data for designing and training the network solutions are collected from numerical simulations using finite element methodology (FEM), which are subsequently validated by experiments. The results demonstrate that the proposed LSTM-based approach outperforms traditional identification techniques in predicting the material hardening parameters. This suggests that the developed procedure can be effectively applied to efficiently characterize different materials, especially those extensively used in industrial applications, ranging from mild steels to advanced high-strength steels.

This paper presents the development of virtual labs for teaching Industrial Robotics programming where theoretical contents are blended with the use of an industrial simulation software package - RobotStudio. The use of this software provides multiple functionalities not only at the theoretical concepts level but also at the implementation level. Sample virtual labs created for the development of student's assignments are described that emphasize the pedagogical value of the learning process. Two examples of lab assignments are presented and discussed. The use of industrial software to create realistic robotic cells proved to be a valuable tool for teaching purposes.

This study aims to explore the use of force vs. time data obtained from an isometric handgrip test to match a frailty state based on the TFI score. BodyGrip, a novel prototype system, is used for handgrip strength over 10 s time interval tests. A cross-sectional study with a non-probabilistic sample of community-dwelling elderly women was conducted. The force/time data collected from the dominant handgrip strength test, together with the Tilburg Frailty Indicator (TFI) test results, were used to train artificial neural networks. Different models were tested, and the frailty matching of TFI scores reached a minimum accuracy of 75%. Despite the small sample size, the BodyGrip system appears to be a promising tool for exploring new frailty-related features. The adopted strategy foresees ultimately configuring the system to be used as an expedite mode for identifying individuals at risk, allowing an easy, quick, and frequent person-centered care approach. Additionally, it is suitable for following up of the elderly in particular, and it may assume a relevant role in the mitigation of the increase in frailty evolution during and after the imposed isolation of the COVID-19 pandemic. Further use of the system will improve the robustness of the artificial neural network algorithm.