TY - JOUR

T1 - Enabling laser transmission welding of additively manufactured thermoplastic parts using an expert system based on neural networks

AU - Kuklik, Julian

AU - Mente, Torben

AU - Wippo, Verena

AU - Jaeschke, Peter

AU - Kaierle, Stefan

AU - Overmeyer, Ludger

N1 - Funding Information: The IGF-project “Qualitätssicherung beim Laserstrahlschweißen additiv gefertigter thermoplastischer Bauteile -QualLa” (No. 21571N) of the Research Community for Quality (FQS), August-Schanz-Straße 21A, 60433 Frankfurt/Main, has been funded by the AiF within the programme for sponsorship by Industrial Joint Research (IGF) of the German Federal Ministry of Economic Affairs and Climate Action based on an enactment of the German Parliament.

PY - 2022/11

Y1 - 2022/11

N2 - In order to use laser transmission welding (LTW) for additively manufactured parts such as prototypes, small series, or one-off products, an enhanced process knowledge is needed to overcome the difficulties in the part composition resulting from the additive manufacturing process itself. In comparison to an injection molding process for thermoplastic parts, the additive manufacturing process fused deposition modeling leads to an inhomogeneous structure with trapped air inside the volume. In this paper, a neural network-based expert system is presented that provides the user with process knowledge in order to improve the weld seam quality of laser welded additively manufactured parts. Both additive manufacturing and LTW process are assisted by the expert system. First, the designed expert system supports the user in setting up the additive manufacturing process to increase the transmissivity. During welding, the additive manufacturing and LTW process parameters are used to predict the weld seam strength. To create the database for the expert system, specimens of transparent and black polylactide are additively manufactured. In order to change the transmissivity at an emission wavelength of 940 nm of the diode laser used, the manufacturing parameters for the transparent parts are varied. The transmissivity of the parts is measured with a spectroscope. The transparent samples are welded to the black samples with laser powers between 8 and 14 W in the overlap configuration and shear tensile tests are performed. In this work, the predictions of the transmissivity and the shear tensile force are demonstrated with an accuracy of more than 88.1% of the neural networks used for the expert system.

AB - In order to use laser transmission welding (LTW) for additively manufactured parts such as prototypes, small series, or one-off products, an enhanced process knowledge is needed to overcome the difficulties in the part composition resulting from the additive manufacturing process itself. In comparison to an injection molding process for thermoplastic parts, the additive manufacturing process fused deposition modeling leads to an inhomogeneous structure with trapped air inside the volume. In this paper, a neural network-based expert system is presented that provides the user with process knowledge in order to improve the weld seam quality of laser welded additively manufactured parts. Both additive manufacturing and LTW process are assisted by the expert system. First, the designed expert system supports the user in setting up the additive manufacturing process to increase the transmissivity. During welding, the additive manufacturing and LTW process parameters are used to predict the weld seam strength. To create the database for the expert system, specimens of transparent and black polylactide are additively manufactured. In order to change the transmissivity at an emission wavelength of 940 nm of the diode laser used, the manufacturing parameters for the transparent parts are varied. The transmissivity of the parts is measured with a spectroscope. The transparent samples are welded to the black samples with laser powers between 8 and 14 W in the overlap configuration and shear tensile tests are performed. In this work, the predictions of the transmissivity and the shear tensile force are demonstrated with an accuracy of more than 88.1% of the neural networks used for the expert system.

UR - http://www.scopus.com/inward/record.url?scp=85141151858&partnerID=8YFLogxK

U2 - 10.2351/7.0000787

DO - 10.2351/7.0000787

M3 - Article

AN - SCOPUS:85141151858

VL - 34

JO - Journal of laser applications

JF - Journal of laser applications

SN - 1042-346X

IS - 4

M1 - 042022

T2 - International Congress of Applications of Lasers & Electro-Optics (ICALEO® 2022)

Y2 - 17 October 2022 through 20 October 2022

ER -