Process Parameter Prediction for Fused Deposition Modeling Using Invertible Neural Networks

Pelzer, Lukas; Posada-Moreno, Andrés Felipe; Müller, Kai; Greb, Christoph; Hopmann, Christian

doi:10.3390/polym15081884

Cited by 4 publications

(1 citation statement)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For practical applications, it is necessary to further optimize the mechanical properties. Literature reports have revealed that proper adjustment in the input parameters (related to both machine and geometry) could lead to improvement in the properties of the FDM 3D prototypes. − Thus, we believe that by regulating the interlayer angle of the printed TPU filaments through the FDM, continuous TPU porous scaffolds with different mechanical properties will be obtained, and thus, CNT/TPU CPCs with improved mechanical properties could be achieved, which has not been reported.…”

Section: Introductionmentioning

confidence: 99%

3D-Printed Co-continuous Segregated CNT/TPU Composites with Superb Electromagnetic Interference Shielding and Excellent Mechanical Properties

Niu

Yang

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Segregated conductive polymer composites (CPCs) have important application prospects in the field of electromagnetic interference (EMI) shielding but suffer from weak mechanical properties that significantly limit their practical applications. In this work, three-dimensional (3D) printing is employed to construct continuous thermoplastic polyurethane (TPU) scaffolds with different interlayer angles of π/5, π/4, π/3, 2π/5, and π/2. Subsequent carbon nanotube (CNT) dip-coating and hot-pressing lead to the successful fabrication of co-continuous segregated CNT/TPU (CNT/TPU-CCS) composites. It is found that the composites not only achieve high EMI shielding properties but also obtain excellent mechanical properties. With only 4.0 wt % of CNT, the CNT/TPU-CCS composites with the interlayer angle of π/3 (CNT/TPU-CCS-π/3) exhibit a high electrical conductivity of 42.2 S/m and a remarkable EMI shielding effectiveness (EMI SE) of 43.1 dB, which are 75% and 72%, respectively, higher than that of the CNT/TPU composites with conventional segregated structure. The CNT/TPU-CCS-π/3 composites also have superior mechanical properties, showing a tensile strength and elongation at break of 17.8 MPa and 377.3%, respectively, which are 196.8% and 1540.6% higher than those of the conventional segregated CNT/TPU composite. This work provides a new facile, economic, and efficient strategy to construct segregated CPCs with both high EMI shielding performance and mechanical properties, and could promote the practical application of segregated CPCs in the next-generation electronic devices.

show abstract

Section: Introductionmentioning

confidence: 99%

3D-Printed Co-continuous Segregated CNT/TPU Composites with Superb Electromagnetic Interference Shielding and Excellent Mechanical Properties

Niu

Yang

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

Improving Shop Floor-Near Production Management Through Data-Driven Insights

Schmitt

Kiesel

Buschmann

et al. 2023

Interdisciplinary Excellence Accelerator Series

View full text Add to dashboard Cite

In short-term production management of the Internet of Production (IoP) the vision of a Production Control Center is pursued, in which interlinked decision-support applications contribute to increasing decision-making quality and speed. The applications developed focus in particular on use cases near the shop floor with an emphasis on the key topics of production planning and control, production system configuration, and quality control loops.Within the Predictive Quality application, predictive models are used to derive insights from production data and subsequently improve the process- and product-related quality as well as enable automated Root Cause Analysis. The Parameter Prediction application uses invertible neural networks to predict process parameters that can be used to produce components with desired quality properties. The application Production Scheduling investigates the feasibility of applying reinforcement learning to common scheduling tasks in production and compares the performance of trained reinforcement learning agents to traditional methods. In the two applications Deviation Detection and Process Analyzer, the potentials of process mining in the context of production management are investigated. While the Deviation Detection application is designed to identify and mitigate performance and compliance deviations in production systems, the Process Analyzer concept enables the semi-automated detection of weaknesses in business and production processes utilizing event logs.With regard to the overall vision of the IoP, the developed applications contribute significantly to the intended interdisciplinary of production and information technology. For example, application-specific digital shadows are drafted based on the ongoing research work, and the applications are prototypically embedded in the IoP.

show abstract

Improving Shop Floor-Near Production Management Through Data-Driven Insights

Schmitt,

Kiesel,

Buschmann

et al. 2023

Interdisciplinary Excellence Accelerator Series

View full text Add to dashboard Cite

In short-term production management of the Internet of Production (IoP) the vision of a Production Control Center is pursued, in which interlinked decision-support applications contribute to increasing decision-making quality and speed. The applications developed focus in particular on use cases near the shop floor with an emphasis on the key topics of production planning and control, production system configuration, and quality control loops.Within the Predictive Quality application, predictive models are used to derive insights from production data and subsequently improve the process- and product-related quality as well as enable automated Root Cause Analysis. The Parameter Prediction application uses invertible neural networks to predict process parameters that can be used to produce components with desired quality properties. The application Production Scheduling investigates the feasibility of applying reinforcement learning to common scheduling tasks in production and compares the performance of trained reinforcement learning agents to traditional methods. In the two applications Deviation Detection and Process Analyzer, the potentials of process mining in the context of production management are investigated. While the Deviation Detection application is designed toidentify and mitigate performance and compliance deviations in production systems, the Process Analyzer concept enables the semi-automated detection of weaknesses in business and production processes utilizing event logs.With regard to the overall vision of the IoP, the developed applications contribute significantly to the intended interdisciplinary of production and information technology. For example, application-specific digital shadows are drafted based on the ongoing research work, and the applications are prototypically embedded in the IoP.

show abstract

Process Parameter Prediction for Fused Deposition Modeling Using Invertible Neural Networks

Cited by 4 publications

References 33 publications

3D-Printed Co-continuous Segregated CNT/TPU Composites with Superb Electromagnetic Interference Shielding and Excellent Mechanical Properties

3D-Printed Co-continuous Segregated CNT/TPU Composites with Superb Electromagnetic Interference Shielding and Excellent Mechanical Properties

Improving Shop Floor-Near Production Management Through Data-Driven Insights

Improving Shop Floor-Near Production Management Through Data-Driven Insights

Contact Info

Product

Resources

About