PRPascal Rabe

Pascal Rabe

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Pascal Rabe has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Generalization of convolutional neural networks for defect detection in friction stir welding towards the qualification of a spindle-integrated high granularity process-force measurement system

    by P. Rabe, A. Schiebahn, U. Reisgen, A. Strachkov, M. Fey, C. Brecher

    Friction Stir Welding (FSW) is a solid-state welding process, which has strongly impacted welding technology, particularly for aluminum alloy applications. Reliable in-line process monitoring is not yet available for most common defects and downstream non-destructive and intermittent destructive testing are generally employed to validate weld seam quality. To reduce cost and production time significant efforts have been undertaken in the recent past to develop process-monitoring systems for FSW based on the evaluation of transient process-data. Neural Networks have been used widely to analyse FSW-process data and evaluate the process characteristics or weld seam quality. The data analysed includes welding parameters, thermal-/acoustic-measurement, image or video data and, most notably, the distinct and descriptive process feedback forces and torque. In this study, conducted within the scope of RWTH Aachen’s Cluster of Excellence (Internet of Production), a high granularity direct force measurement setup, which was adapted to the production environment, by integrating reliable, cost-efficient sensors into the machining spindle, was used. Weld data was recorded over a wide range of FSW applications with varying weld-parameters and Al-alloys. Convolutional Neural Networks (CNN) that were previously developed based on measurements of external force and torque sensors were adapted to evaluate the higher granularity data of the new sensor-system and detect volumetric defects within the welds. Good generalization was shown across the weld parameter sets, alloys and welding tool. An average classification accuracy of 98.04% was achieved over three network trainings. Due to the segmentation of data for the evaluation 100% of internal defects were successfully detected by each network iteration. The developed solution aims at offering a highly reliable, spindle integrated and cost-efficient quality monitoring solution for FSW to replace the required expensive and time-consuming testing.


  • Open Access

    Development and validation of a generalized, AI-based inline void defect detection solution for FSW based on force feedback

    by P. Rabe, A. Schiebahn, U. Reisgen

    Friction stir welding is a solid-state joining process that operates below the material’s melting point commonly used to join aluminum parts, avoiding the drawbacks of fusion-based methods. These resulting advantages have accelerated growth and are increasing the number of applications across a range of industrial sectors, many of which are safety–critical. Along with the increase in applications and rise in productivity the need for reliable and cost-effective, non-destructive inline quality monitoring is rapidly growing. This publication is based on the research group’s ongoing efforts to develop a capable generalized inline-monitoring solution. To detect and classify FSW defects, convolutional neural networks (CNNs) based on the DenseNet architecture are used to evaluate recorded process data. The CNNs are modified to include weld and workpiece-specific metadata in the classification. These networks are then trained to classify transient weld data over a wide range of welding parameters, three different Al alloys, and two sheet thicknesses. The hyperparameters are incrementally tuned to increase weld defect detection. The defect detection threshold is tuned to prevent false negative classifications by adjusting the cost function to fit the needs of a force-based detection system. Classification accuracies > 99% are achieved with multiple neural network configurations. System validation is provided utilizing a newly recorded weld dataset from a different welding machine with previously used parameter/workpiece combinations as well as parameter combinations and alloys as well as sheet thicknesses outside the training parameter range. The generalization capabilities are demonstrated by the detection of > 99.9% of weld defects in the validation data.


  • Open Access

    Model-Based Controlling Approaches for Manufacturing Processes

    by Adrian Karl Rüppel, Muzaffer Ay, Benedikt Biernat, Ike Kunze, Markus Landwehr, Samuel Mann, Jan Pennekamp, Pascal Rabe, Mark P. Sanders, Dominik Scheurenberg, et al.

    The main objectives in production technology are quality assurance, cost reduction, and guaranteed process safety and stability. Digital shadows enable a more comprehensive understanding and monitoring of processes on shop floor level. Thus, process information becomes available between decision levels, and the aforementioned criteria regarding quality, cost, or safety can be included in control decisions for production processes. The contextual data for digital shadows typically arises from heterogeneous sources. At shop floor level, the proximity to the process requires usage of available data as well as domain knowledge. Data sources need to be selected, synchronized, and processed. Especially high-frequency data requires algorithms for intelligent distribution and efficient filtering of the main information using real-time devices and in-network computing. Real-time data is enriched by simulations, metadata from product planning, and information across the whole process chain. Well-established analytical and empirical models serve as the base for new hybrid, gray box approaches. These models are then applied to optimize production process control by maximizing the productivity under given quality and safety constraints. To store and reuse the developed models, ontologies are developed and a data lake infrastructure is utilized and constantly enlarged laying the basis for a World Wide Lab (WWL). Finally, closing the control loop requires efficient quality assessment, immediately after the process and directly on the machine. This chapter addresses works in a connected job shop to acquire data, identify and optimize models, and automate systems and their deployment in the Internet of Production (IoP).


  • Open Access

    Model-Based Controlling Approaches for Manufacturing Processes

    by Adrian Karl Rüppel, Muzaffer Ay, Benedikt Biernat, Ike Kunze, Markus Landwehr, Samuel Mann, Jan Pennekamp, Pascal Rabe, Mark P. Sanders, Dominik Scheurenberg, et al.

    The main objectives in production technology are quality assurance, cost reduction, and guaranteed process safety and stability. Digital shadows enable a more comprehensive understanding and monitoring of processes on shop floor level. Thus, process information becomes available between decision levels, and the aforementioned criteria regarding quality, cost, or safety can be included in control decisions for production processes. The contextual data for digital shadows typically arises from heterogeneous sources. At shop floor level, the proximity to the process requires usage of available data as well as domain knowledge. Data sources need to be selected, synchronized, and processed. Especially high-frequency data requires algorithms for intelligent distribution and efficient filtering of the main information using real-time devices and in-network computing. Real-time data is enriched by simulations, metadata from product planning, and information across the whole process chain. Well-established analytical and empirical models serve as the base for new hybrid, gray box approaches. These models are then applied to optimize production process control by maximizing the productivity under given quality and safety constraints. To store and reuse the developed models, ontologies are developed and a data lake infrastructure is utilized and constantly enlarged laying the basis for a World Wide Lab (WWL). Finally, closing the control loop requires efficient quality assessment, immediately after the process and directly on the machine. This chapter addresses works in a connected job shop to acquire data, identify and optimize models, and automate systems and their deployment in the Internet of Production (IoP).


  • Open Access

    Model-Based Controlling Approaches for Manufacturing Processes

    by Adrian Karl Rüppel, Muzaffer Ay, Benedikt Biernat, Ike Kunze, Markus Landwehr, Samuel Mann, Jan Pennekamp, Pascal Rabe, Mark P. Sanders, Dominik Scheurenberg, et al.

    The main objectives in production technology are quality assurance, cost reduction, and guaranteed process safety and stability. Digital shadows enable a more comprehensive understanding and monitoring of processes on shop floor level. Thus, process information becomes available between decision levels, and the aforementioned criteria regarding quality, cost, or safety can be included in control decisions for production processes. The contextual data for digital shadows typically arises from heterogeneous sources. At shop floor level, the proximity to the process requires usage of available data as well as domain knowledge. Data sources need to be selected, synchronized, and processed. Especially high-frequency data requires algorithms for intelligent distribution and efficient filtering of the main information using real-time devices and in-network computing. Real-time data is enriched by simulations, metadata from product planning, and information across the whole process chain. Well-established analytical and empirical models serve as the base for new hybrid, gray box approaches. These models are then applied to optimize production process control by maximizing the productivity under given quality and safety constraints. To store and reuse the developed models, ontologies are developed and a data lake infrastructure is utilized and constantly enlarged laying the basis for a World Wide Lab (WWL). Finally, closing the control loop requires efficient quality assessment, immediately after the process and directly on the machine. This chapter addresses works in a connected job shop to acquire data, identify and optimize models, and automate systems and their deployment in the Internet of Production (IoP).


  • Open Access

    Non-destructive evaluation of the friction stir welding process, generalizing a deep neural defect detection network to identify internal weld defects across different aluminum alloys

    by P. Rabe, U. Reisgen, A. Schiebahn

    Friction stir welding (FSW) is a solid-state welding process, which has significantly disrupted welding technology particularly for aluminum alloy applications. Due to its high-quality welds in all aluminum alloys, comparatively low heat input with high energy efficiency and ecological friendliness, FSW is used in a rapidly growing number of applications. Currently, destructive and non-destructive testing methods are attached as a separate process step to verify weld seam quality, detecting imperfections late in production and requiring costly rework or scrapping of the assembly. Various studies have shown the possibility of using deep neural networks (DNN) to evaluate weld quality and detect welding defects based on recorded data. In this study, conducted within the scope of RWTH Aachen’s Cluster of Excellence, Internet of Production, recurrent neural networks (RNN), and convolutional neural networks (CNN) were successfully trained to classify FSW force data sets, generated while joining different aluminum alloys over a wide range of welding parameters. For internal weld defects bigger than 0.08 mm, detection accuracies over 95% were achieved using bidirectional long short-term memory (BiLSTM) networks when limited to a single alloy and thickness. The classification accuracy dropped to ~ 90% when using multiple alloys and sheet thicknesses. The comparison between different network types’ classification accuracy as well as their ability to generalize the defect detection across different welding tasks with varying sheet thicknesses, respective welding tools, and different Al alloys is shown. The systems aim at offering a reliable and cost-efficient quality monitoring solution with a wide range of applicability, increasing the acceptance of the friction stir welding process as well as confidence in the resulting weld seam quality.


  • Open Access

    Force feedback-based quality monitoring of the friction stir welding process utilizing an analytic algorithm

    by P. Rabe, A. Schiebahn, U. Reisgen

    The friction stir welding (FSW) process is known as a solid-state welding process, comparatively stable against external influences. Therefore, the process is commonly used with fixed welding parameters, utilizing axial force control or position control strategies. External and internal process disturbances introduced by workpiece, gap tolerance, tool wear, or machine/tool inadequacies are rarely monitored, and conclusions about the weld seam quality, based on the recorded process data, are not drawn. This paper describes an advancement, improving on research into the correlation of process force feedback events or gradual force changes and the resulting weld seam characteristics. Analyzing the correlation between examined weld sections and high-resolution rate force data, a quality monitoring system based on an analytic algorithm is described. The monitoring system is able to accurately distinguish sound welds from such with internal (void) and external (flash) defects.