Abstract
This work describes an algorithm which is able to determine the working states of a rotating cutting assembly automatically. The approach was validated at a self-propelled forage harvester under different environmental and harvest conditions. Data were recorded throughout different field trials near the cutting assembly using two built-in vibration sensors. The working states of the cutting assembly were divided into processing, neutral and grinding. The analysis was performed using evolutionary optimized Artificial Neural Networks. The generated models for classification are able to determine the working states robustly for this type of a rotating cutting assembly. Case-specific and sensor-specific confusion matrices are presented for performance evaluation. As a conclusion vibration data is suitable for automatic and robust classification in this context.
Zusammenfassung
Dieser Beitrag beschreibt einen Algorithmus, der die Arbeitszustände einer rotierenden Schneidanordnung automatisiert bestimmen kann. Der Bewertungsansatz wurde unter Verwendung eines selbstfahrenden Feldhäckslers unter verschiedenen Umgebungs- und Erntebedingungen validiert. Die Daten wurden in Feldversuchen über zwei Vibrationssensoren an der Schneideinrichtung, bzw. der Messertrommel, erfasst. Die Arbeitszustände der Schneidanordnung wurden in Verarbeitung, Leerlauf und Schleifvorgang unterteilt. Die Analyse dieser Zustände wurde unter Verwendung von evolutionär optimierten Künstlichem Neuronalen Netzen durchgeführt. Die generierten Modelle sind in der Lage, die Arbeitszustände für diese Art einer Schneidanordnung robust zu klassifizieren. Sensorspezifische Vertauschungsmatrizen werden, bezogen auf die jeweiligen Feldversuche, für die Leistungsbewertung vorgelegt. Als eine Schlussfolgerung ist festzustellen, dass die Schwingungsdaten in diesem Kontext für eine robuste Analyse geeignet sind.
About the authors
Dr.-Ing. Christian Walther is scientific assistant at the Faculty of Electrical Engineering at the Schmalkalden University of Applied Sciences in Germany. There he is working in the research group for Embedded Diagnostic Systems. He is also working as deputy group leader of the Embedded Systems group at the Advanced System Technology (AST), Branch of Fraunhofer Institute of Optronics, System Technologies and Image Exploitation in Ilmenau, Germany. His work focuses on the following areas: signal analysis, machine learning and embedded systems.
University of Applied Sciences Schmalkalden, Faculty of Electrical Engineering, Blechhammer 4–9, D-98574 Schmalkalden, Germany, and Fraunhofer Institute of Optronics, System Technologies and Image Exploitation, Advanced System Technologies, Am Vogelherd 50, D-98693 Ilmenau, Germany
Prof. Dr.-Ing. Andreas Wenzel is professor for embedded systems and computer sciences at the Schmalkalden University of Applied Sciences in Germany. He is founder and head of the research group fo Embedded Diagnostic Systems. Additionally he is the leader of the Embedded Systems group at the Advanced System Technology (AST), Branch of Fraunhofer Institute of Optronics, System Technologies and Image Exploitation in Ilmenau, Germany. His main field of work is the development of methods for diagnostic, prediction and classification and their implementation in embedded systems.
University of Applied Sciences Schmalkalden, Faculty of Electrical Engineering, Blechhammer 4–9, D-98574 Schmalkalden, Germany, and Fraunhofer Institute of Optronics, System Technologies and Image Exploitation, Advanced System Technologies, Am Vogelherd 50, D-98693 Ilmenau, Germany
Frank Beneke was born in Recklinghausen, Germany, in 1970. He received the degree Diplom-Ingenieur in mechanical engineering from the Ruhr-University of Bochum, Germany, in 1998 and the Ph.D. degree in mechanical engineering from Essen University, Germany, in 2003. From 1998 to 2003, he was a Research Assistant with the Chair of Product Development (Bochum) and the Chair of Product Development (Duisburg-Essen). From 2004 to 2008 he was a Specialist for Product Development and Benchmarking and Project Manager in a company of the automotive supplier industry. From 2008 to 2016, he has been a Professor with the Mechanical Engineering Department, Schmalkalden University of Applied Sciences, Schmalkalden, Germany. From 2016 he is a Professor for Agricultural Engineering with the Faculty of Agricultural Sciences, Georg-August-University, Göttingen, Germany. He is author of several articles, and conference contributions. His research interests include agricultural engineering and process chains in agriculture, condition monitoring in agricultural equipment, biomass as renewable resource and necessary equipment for harvesting, post-harvest technologies in non-food and the use of 3D-printing for development of agricultural equipment.
University of Goettingen, Department of Crop Sciences, Section of Agricultural Engineering, Gutenbergstrasse 33, D-37075 Goettingen, Germany
Oliver Jorg Hensel, born June 18th, 1962 , Dülken (Germany). Qualifications: BSc Agriculture (Göttingen University), MSc Agricultural Engineering (Hohenheim University), Dr.sc.agr. Agricultural Engineering in the Tropics and Subtropics (Hohenheim University). Current Position: Full Professor for Agricultural and Biosystems Engineering at the Faculty of Organic Agricultural Sciences at the University of Kassel (2004-2015: `C4', 2016 – today: `W3'); Founder Member of the International Centre for Decent Work and Development – “Higher Education Excellence in Development Co-operation” by DAAD and the German Federal Ministry for Economic Cooperation and Development (BMZ). Previous Appointments: Senior scientist (-1999) at Hohenheim University, Stuttgart (Department of Agricultural Engineering in the Tropics and Subtropics); Managing Director of an International Engineering Office for Food Processing Machinery, Böblingen (1999-2004). International Experience: Up to now around 70 own major scientific projects worldwide, special focus on Africa and Asia, numerous business relations all around the world while working in industry. Selected University and Professional Services: Elected Member of the Faculties Convent, Member of the Scientific Committee `Enviromental Technology VDI - KUT' (Association of German Engineers), Committee member of DLG - German Agricultural Society and KTBL – Association for Technology and Structures in Agriculture. Reviewer for academic societies such as DFG, VW-Foundation, Humbold Foundation and for several scientific journals. Member of High Level Panel of Experts on Food Security and Nutrition (HLPE) of the UN Committee on World Food Security (CFS), Faculties appointee for University-Based Start-Ups / Entrepreneurship. Awards: Excellency in Teaching, Award of the State of Baden-Württemberg (2004), Hans- Martin-Prize of occupational sciences (2008), UNESCO Award “Education for Sustainable Development” (2010), several innovation awards and patent.
University of Kassel, Agricultural Engineering, Nordbahnhofstrasse 1a, D-37213 Witzenhausen, Germany
Dipl.-Ing. Jochen Huster was born in Harsewinkel, Germany, in 1963. He received his Diploma in 1990 at University of Applied Sciences at Bielefeld. Since then he worked at CLAAS electronic development and predevelopment for more than 25 years. He is managing different projects for CLAAS, therefore developing soft- and hardware, bringing new technologies into agriculture business and is also testing on the field.
CLAAS Selbstfahrende Erntemaschinen GmbH, Advanced Engineering Electronics, Münsterstr. 33, D-33428 Harsewinkel, Germany
Acknowledgement
The project was supported by funds of the German Governments Special Purpose Fund held at Landwirtschaftliche Rentenbank.
©2017 Walter de Gruyter Berlin/Boston