Data Mining and Machine Learning Methods Applied to A Numerical Clinching Model

Götz, Marco; Leichsenring, Ferenc; Kropp, Thomas; Muller, Peter A.; Falk, Tobias; Graf, Wolfgang; Kaliske, Michael; Drossel, Welf‐Guntram

doi:10.31614/cmes.2018.04112

Cited by 5 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DL has many architectures, especially in mechanics, and research is focused mainly on using the feed-forward neural network (FFNN), recurrent neural network (RNN), and convolutional neural network (CNN). So far, applications of these types of neural networks devoted to the field of mechanics can be seen in the recent works of [27][28][29][30][31][32][33][34][35][36][37][38][39][40][41][42][43]. A detailed description of those approaches is summarized as follows:…”

Section: Deep Learning (Dl) Architecturesmentioning

confidence: 99%

Feed-Forward Neural Networks for Failure Mechanics Problems

2021

View full text Add to dashboard Cite

This work addresses an efficient neural network (NN) representation for the phase-field modeling of isotropic brittle fracture. In recent years, data-driven approaches, such as neural networks, have become an active research field in mechanics. In this contribution, deep neural networks—in particular, the feed-forward neural network (FFNN)—are utilized directly for the development of the failure model. The verification and generalization of the trained models for elasticity as well as fracture behavior are investigated by several representative numerical examples under different loading conditions. As an outcome, promising results close to the exact solutions are produced.

show abstract

Section: Deep Learning (Dl) Architecturesmentioning

confidence: 99%

Feed-Forward Neural Networks for Failure Mechanics Problems

2021

View full text Add to dashboard Cite

show abstract

“…In addition to the available information of the geometric dimensions of the tools, the spring rate of the blankholder and the joining speed, the friction conditions as well as the material properties are important for an exact modeling of the numerical simulation. Due to numerous past projects in which clinch simulations were considered [9,11,12], the gained expertise is used and the shear approach is applied for the friction. The selected friction factors have been determined on the base of the already performed numerical computations of the clinching process.…”

Section: Numerical Simulationmentioning

confidence: 99%

Clinching with divided punch to prevent critical neck thicknesses

Falk

2023

Materials Research Proceedings

View full text Add to dashboard Cite

Abstract. Clinching thin sheet metal into a thicker part can result in low neck thicknesses or even neck cracks. How these critical low values for neck thickness can be counteracted is described in this paper, using a two-part punch, which is devided in an inner and outer unit. At the beginning, both move parallel in the direction of the die until the outer punch stops at a defined position and only the inner one moves further down and forms the clinch point, with its characteristic contour and the geometric values of interlock and neck thickness. Due to the large punch diameter at the beginning of the process, more material initially flows into the neck area than in conventional clinching, so that a greater neck thickness can be achieved. Numerical simulation was used to create the concept and verify it experimentally. The greater neck thickness has a positive effect on the shear tensile strength and can also be transferred to the typical joining direction for clinching (thick into thin material).

show abstract

“…The process modelling can be facilitated by the use of machine learning methods. For example, approaches for joining processes are shown in [102] and [103]. An approach for self-piercing riveting is presented in [104] on the basis of local fuzzy pattern models with a multidimensional membership function that can be utilized for process control based on the prediction of a series of relevant output parameters.…”

Section: Manufacture Of Self-piercing Rivets Using High Nitrogen Steelmentioning

confidence: 99%

Mechanical joining of high-strength multi-material systems − trends and innovations

Merklein

Jäckisch

Kuball

et al. 2023

Mechanics & Industry

View full text Add to dashboard Cite

In conjunction with mechanical joining processes. Mechanical joining processes play a key role for the realization of multi-material lightweight structures, which are essential with regard to environmental protection. However, joining of dissimilar high-strength materials is challenging due to the varying properties of the joining partners and due to their high flow stresses and often limited ductility. Thus, the evolution of established processes as well as the development of innovative and highly productive joining technologies are necessary. Requirements for a highly volatile production environment are versatility, flexibility, resilience and robustness. Within this contribution, current trends and innovations related to selected mechanical joining processes for enabling the material mix are outlined in order to point out opportunities to address these requirements in the future. In this context, joining using cold formed pin structures is presented as a promising approach for connecting dissimilar materials like metals to fibre-reinforced plastics. Furthermore, it is shown how the shear-clinching technology can be combined with a process-adapted application of locally limited heat treatment in order to promote the joinability and control the material flow during joining. A novel approach for reducing process forces and expanding process windows is the use of ultrasonic assistance for mechanical joining operations, which is demonstrated by the example of a nut staking process with superimposed high frequency oscillation. As concerns the widely used self-piercing riveting technique, current research activities relate not only to the further development of the joining process itself, for example by combining self-piercing riveting and tumbling, but also to the use of new rivet materials like high strain hardening stainless steels. In addition, the evolution towards mechanical joining 4.0 against the background of data-based process control in conjunction with of mechanical joining processes is also subject of the considerations.

show abstract

Data Mining and Machine Learning Methods Applied to A Numerical Clinching Model

Cited by 5 publications

References 21 publications

Feed-Forward Neural Networks for Failure Mechanics Problems

Feed-Forward Neural Networks for Failure Mechanics Problems

Clinching with divided punch to prevent critical neck thicknesses

Mechanical joining of high-strength multi-material systems − trends and innovations

Contact Info

Product

Resources

About