wbk Institute of Production Science

New Publications

[ 1 ] Qu, J.; Barton, D.; Gönnheimer, P.; Pinsker, F.; Kufer, D. & Fleischer, J. (2020), "Self-Aware LiDAR Sensors in Autonomous Systems using a Convolutional Neural Network". Intelligent, Flexible and Connected Systems in Products and Production, eds. Thoben, K.; Dekena, B.; Lang, W. & Trächtler, A., Elsevier, pp. 50-55.
Abstract
Autonomous systems, as found in autonomous driving and highly automated production systems, require an increased reliability in order to achieve their high economic potential. Self-aware sensors are a key component in highly reliable autonomous systems. In this paper we highlight a proof of concept (PoC) of a deep learning method that enables a LiDAR (Light detection and ranging) sensor to detect functional impairment. More specifically, a deep convolutional neural network (CNN) is developed and trained with labelled LiDAR data in the form of point clouds to classify the degree of impairment of its functionality. The results are statistically significant and can be regarded as a general classifier for objects within LiDAR data, applied to selected cases of sensor impairment. In detecting impairment and evaluating the correctness of the captured data, the sensor gains a basic form of self-awareness. The presented methods and insights pave the way for improved safety of autonomous systems by the means of more sophisticated ?self-aware? neural networks.

[ 2 ] Schulze, V. & Vargas, B. (2020), "Wälzschälen mit kleinen Achskreuzwinkeln" Forschungsvereinigung Antriebstechnik e.?V., Frankfurt am Main.
Abstract
Die Herstellung von Verzahnungen neben Störkonturen ist aufgrund des benötigten Werkzeugauslaufs eingeschränkt. Um diese Bauteile durch das Wälzschälen fertigen und somit das Verfahren auf das Bauteilspektrum des Wälzstoßens anwenden zu können, muss der verfahrensbedingte Werkzeugauslauf durch die Reduzierung des Achskreuzwinkels möglichst klein gehalten werden. Zielsetzung des Vorhabens war die Untersuchung der Wirtschaftlichkeit und der technologischen Grenzen des Wälzschälens mit kleinen Achskreuzwinkeln. Zu Beginn wurde ein Kollisionsmodell entwickelt und eine Parameterstudie für das Demonstratorbauteil durchgeführt, wobei die Einflüsse von Achskreuzwinkel, Werkzeugdurchmesser und Außermittigkeit untersucht wurden. Anschlie?end wurden die Einflüsse der Spanungsdicke, des Kopfspanwinkels und der Schnittaufteilung für Achskreuzwinkel zwischen 5? und 15? experimentell untersucht. Hierbei deuten die Ergebnisse aus den Verschleißuntersuchungen und die Analyse lokaler Spanungskenngrößen auf eine Grenze hinsichtlich des minimalen Spanwinkels hin, welcher als wichtigste Auslegungskenngröße für kleine Achskreuzwinkel anzusehen ist. Anschließend erfolgte die Übertragung der Ergebnisse der Versuche an 16MnCr5 auf einen zweitenWerkstoff 30CD12. Die instabilen Prozesse und sehr kurzen Standwege verdeutlichen, dass die identifizierte Prozessgrenze stark materialabhängig ist. Letztendlich wurden Richtlinien abgeleitet, die Aussagen zur Anwendbarkeit des Wälzschälens in Abhängigkeit des vorhandenen Freiraums ermöglichen.

[ 3 ] Liebrecht, C.; Kandler, M.; Lang, M.; Schaumann, S.; Stricker, N.; Wuest, T.; Lanza, G. & , . (2020), "Decision support for the implementation of Industry 4.0 methods - ", Journal of Manufacturing Systems, [30.11.-1].
Abstract
The economically successful implementation of Industry 4.0 methods in industrialcompanies requires a structured introduction process. The main objective of such astructured implementation process is the case-specific analysis and evaluation ofavailable Industry 4.0 methods to select the most suitable ones for an individualcompany. The presented methodology aims to establish a financial, strategic, andbenefit-oriented evaluation approach for Industry 4.0 methods to assess their potential.The core of our methodology is a general Industry 4.0 toolbox providing a structuredclassification of different methods. In the first phase, a limited set of Industry 4.0methods is derived from the toolbox by classification into production typologies. In thesecond phase, all Industry 4.0 methods of the derived set are strategically assessed aswell as evaluated from a monetary perspective. The evaluation of the methods isbased on company-specific characteristics, its strategic focus, and its (market)environment. Based on this evaluation, we develop specific, value-addingimplementation scenarios. In the third phase, the identified implementation scenarioswith their specific order of prioritized methods are simulated in a System Dynamicsmodel. The three phases ultimately result in a recommendation for a company-specificIndustry 4.0 implementation roadmap

[ 4 ] Böttger, D.; Stampfer, B.; Gauder, D.; Straß, B.; Häfner, B.; Lanza, G.; Schulze, V. & Wolter, B. (2020), "Concept for soft sensor structure for turning processes of AISI4140", tm - Technisches Messen, vol. 87, no. 12, pp. 745-756. 10.1515/teme-2020-0054 [30.11.-1].
Abstract
During turning of quenched and tempered AISI4140 surface layer states can be generated, which degrade the lifetime of manufactured parts. Such states may be brittle rehardened layers or tensile residual stresses. A soft sensor concept is presented in this work, in order to identify relevant surface modifications during machining. A crucial part of this concept is the measurement of magnetic characteristics by means of the 3MA-testing (Micromagnetic Multiparameter Microstructure and Stress Analysis). Those measurements correlate with the microstructure of the material, only take a few seconds and can be processed on the machine. This enables a continuous workpiece quality control during machining. However specific problems come with the distant measurement of thin surface layers, which are analyzed here. Furthermore the scope of this work is the in-process-measurement of the tool wear, which is an important input parameter of the thermomechanical surface load. The availability of the current tool wear is to be used for the adaption of the process parameters in order to avoid detrimental surface states. This enables new approaches for a workpiece focused process control, which is of high importance considering the goals of Industry 4.0.

[ 5 ] Barton, D.; Männle, P.; Odendahl, S.; Stautner, M. & Fleischer, J. (2020), "Concept for collision avoidance in machine tools based on geometric simulation and sensor data". Eds. Heizmann, M. & Längle, T., KIT Scientific Publishing, Karlsruhe, pp. 171-182.
Abstract
Collisions are a major cause of unplanned downtime in small series manufacturing with machine tools. Existing solutions based on geometric simulation do not cover collisions due to setup errors. Therefore a concept is developed to enable a sensor-based matching of the setup with the simulation, thus detecting discrepancies. Image processing in the spatial and frequency domain is used to compensate for harsh conditions in the machine, including swarf, fluids and suboptimal illumination.

More publications you will find here: