Filtern
Erscheinungsjahr
- 2021 (2)
Dokumenttyp
Sprache
- Englisch (2)
Referierte Publikation
- ja (2)
Schlagworte
- Artificial neural network (1)
- Directed energy deposition (1)
- ICP-OES (1)
- MicroXRF (1)
- PVDF-based membrane (1)
- TXRF (1)
- UV/VIS (1)
- VRFB (1)
- XANES (1)
Organisationseinheit der BAM
Additive manufacturing, and therefore directed energy deposition, is
gaining more and more interest from industrial users. However, quality assurance for the components produced is still a challenge. Machine learning, especially using artificial neuronal networks, is a potential method for ensuring a high-quality standard. Based on process Parameters and monitoring data, part quality can be predicted. A further advantage is the ability to constantly learn and adopt to slight process changes.
First tests using artificial neural networks focus on the prediction of track geometry. The results show that even a small data set is enough to provide high accuracy in the predictions. In this work, an artificial neural network for the predictive analysis of relative density in laser powder cladding has been developed. A central composite experimental design is used to generate 19 data sets. Input variables are laser power, feed rate and powder mass flow. Cubes are built up where density is considered as a target value. Several neural networks are trained and evaluated with these data sets. Different topologies and initial weights are considered. The best network reaches a confidence level of around 90 % for the prediction of relative density based on the process parameters. Finally, the optimization of the generalization performance is investigated. To this purpose, methods of variation in error limit as well as cross-validation are applied. In this way, density is predictable by an artificial neural network with an accuracy of about 95 %.
A core component of energy storage systems like vanadium redox flow batteries (VRFB) is the polymer electrolyte membrane (PEM). In this work, the frequently used perfluorosulfonic-acid (PFSA) membrane Nafion™ 117 and a novel poly (vinylidene difluoride) (PVDF)-based Membrane are investigated. A well-known problem in VRFBs is the vanadium permeation through the membrane. The consequence of this so-called vanadium crossover is a severe loss of capacity. For a
better understanding of vanadium transport in membranes, the uptake of vanadium ions from electrolytes containing Vdimer(IV–V) and for comparison also V(II), V(III), V(IV), and V(V) by both membranes was studied. UV/VIS spectroscopy, X-ray absorption near edge structure spectroscopy (XANES), total reflection X-ray fluorescence spectroscopy (TXRF), inductively coupled plasma optical emission spectrometry (ICP-OES), and micro X-ray fluorescence spectroscopy (microXRF) were used to determine the vanadium concentrations and the species inside the membrane. The results strongly support that Vdimer(IV–V), a dimer formed from V(IV) and V(V), enters the nanoscopic water-body of Nafion™ 117 as such. This is interesting, because as of now, only the individual ions V(IV) and V(V) were considered to be transported through the membrane. Additionally, it was found that the Vdimer(IV–V) dimer partly dissociates to the individual ions in the novel PVDF-based membrane.
The Vdimer(IV–V) dimer concentration in Nafion™ was determined and compared to those of the other species. After three days of equilibration time, the concentration of the dimer is the lowest compared to the monomeric vanadium species. The concentration of vanadium in terms of the relative uptake λ = n(V)/n(SO3
) are as follows: V(II) [λ = 0.155] > V(III) [λ = 0.137] > V(IV) [λ = 0.124] > V(V) [λ = 0.053] > Vdimer(IV–V) [λ = 0.039]. The results show that the Vdimer(IV–V) dimer Needs to be considered in addition to the other monomeric species to properly describe the transport of vanadium through Nafion™ in VRFBs.