1,720,966 research outputs found
Modell zur Vorhersage von Prozessparametern eines Laserprozesses auf Basis von RGB-Farbwerten
No full textKünstliches neuronales Netz mit zwei verdeckten Schichten mit 50 bzw. 25 Neuronen und einer ReLU-Aktivierungsfunktion. Die Ausgabeschicht hat eine sigmoide Aktivierungsfunktion. Für das Training wird ein Adam-Optimierer verwendet, der den mittleren quadratischen Fehler der Vorhersage gegenüber der erwarteten Ausgabe minimiert und so die Gewichte des Netzes bestimmt.
Eingänge zw. 0 und 1:
b: Blau im RGB-Farbraum
g: Grün im RGB-Farbraum
r: Blau im RGB-Farbraum
Ausgänge zw. 0 und 1:
hatch_um: Der Hatch-Abstand zwischen Scanlinien in µm
power_mw: Die Laserleistung in mW
pulse_us: Die Pulsrate in µs
speed_um_s: Die Scangeschwindigkeit in µm/s
Skaliert wie folgt:
r, b, g: von 0 bis 255 [-]
hatch_um: von 1 bis 100 in [µs]
power_mw: von 1000 bis 20000 in [mW]
pulse_us: von 2 bis 10 in [µs]
speed_um_s: von 41666 bis 3333333 in [µm/s]
Das Modell kann mit dem folgenden Python-Code ausgeführt werden:
from keras.models import load_model
def scale_value(x, new_min, new_max):
scaled_value = (x * (new_max - new_min)) + new_min
return scaled_value
r = 123
b = 231
g = 85
model = load_model('model.keras')
output = model.predict(np.array([b / 255, g / 255, r / 255]).reshape(1, -1))
hatch_um = int(scale_value(output[0][0], 1, 100))
power_mw = int(scale_value(output[0][1], 1000, 20000))
pulse_us = int(scale_value(output[0][2], 2, 10))
speed_um_s = int(scale_value(output[0][3], 41666, 3333333))
</pre
Prozessparameter und Farbwerte für einen Laserprozess auf Edelstahl
No full textBei diesem Versuch wurde eine Edelstahlplatte mit unterschiedlichen Prozessparametern eines Lasersystems belichtet und die resultierende Farbe mit einem Mikroskop ausgewertet.
Die zentralen Komponenten der Laseranlage sind ein Galvanometerscanner (MINISCAN III mit einer Strahleintrittsapertur von 14 mm) der Firma Raylase, ein f -Theta Objektiv (Brennweite 160 mm) und ein gepulster Laser (TruPulse 2002 nano - FK10-RM mit einer mittleren Ausgangsleistung von 20 W und einer Wellenlänge von
1064 nm) der Firma Trumpf.
Jedes belichtete Feld hatte eine Größe von 2 mm.
In Summe wurden 625 Felder mit einer einzigartigen Parameterkombination belichtet. Die verwendeten Parameter sind dabei:
Geschwindigkeiten in mm/min: 30000, 20000, 15000, 10000, 5000
Laserleistung in ‱ (1 pro Zehntausend) von 20 W: 6000, 5000, 4000, 3000, 2000
Pulsrate in μs: 2, 3, 4, 5, 6
Hatch-Abstand in mm: 0.01, 0.005, 0.0025, 0.002, 0.001
</ul
Correlation analysis methods in multi-stage production systems for reaching zero-defect manufacturing
Full text linkBased on the amount of production steps and the related complexity, multi-stage production systems are very error-prone. In order to compensate for this disadvantage and to achieve zero-defect manufacturing, a data-driven approach is needed. The increasing availability of sensor and machine data provides a high informational content of the individual processes, which can be evaluated with appropriate methods. Literature shows various methods of data analysis for examining the correlations of data sets. These methods and strategies are analyzed, hierarchically structured and extended by four developed algorithms. Finally, the data-driven analysis tool is presented and validated using two industrial use cases
A control model for downstream compensation strategy in multi-stage manufacturing systems of complex parts
Full text linkThe capability of delivering high-quality products with the required service level is a key factor for competitiveness in manufacturing companies. Zero-Defect Manufacturing control strategies aim at ensuring these targets grounding on the combination of knowledge extraction from the process and advanced statistical tools. This work presents the approach proposed within the EU-funded project ForZDM for selected use-cases in different industrial sectors characterized by multi-stage manufacturing systems and high-value complex parts. The control model is proposed and the overall control strategy is presented with respect to the state-of-the-art solutions, in order to show a comprehensive methodology integrating the joint product-system quality-oriented approach
Knowledge Capturing Platform in Multi-Stage Production Systems for Zero-Defect Manufacturing
No full textThe increasing complexity of parts and the growing quality requirements pose new challenges for today's manufacturing industry. Multi-Stage Production Systems, which are known for complex links and sequences of many different process steps, must be adapted to these requirements. This means, being cost-effective and flexible while still meeting high quality standards. The idea of Zero-Defect Manufacturing aims to reduce scrap, rework and special operations by analyzing and optimizing multi-stage production systems through data-driven and learning-based approaches. A Knowledge Capturing Platform concept is introduced to extract a deeper understanding from collected data with inter-stage correlation methods, part variation approaches along the line and intelligent monitoring systems
Part Variation Modeling in Multi-Stage Production Systems for Zero-Defect Manufacturing
Full text linkMulti-stage production systems concede for low error and failure margins within every single machining and assembly step to not degrade product quality. Especially during multi-stage production of rotating parts, minor defects during a single step can corrupt a workpiece beyond repair. Since multistage production systems are complex, inter-connected chains of machining steps, a global approach to handling and compensating error emergence and propagation is for reaching Zero-Defect Manufacturing indispensable. We introduce Part Variation Modeling within a knowledge capturing platform to monitor centrally gathered metrological data for deviations. Further, a parametric model is presented allowing for description of rotating parts and enabling identification of deviations at every stage. Based on our inter-stage correlation analysis technique, the parametric model enables description of Part Variation Modes of a piece given current machine states and historic deviation likelihood as will be presented
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
- …
