Tutorials
Tutorial 1 - Measuring, Modeling, and Mitigating Inverter-Induced Bearing Currents
Prof. Annette Muetze, Graz University of Technology, Graz, Austria
Topic - Inverter-induced bearing currents that may occur in modern variable speed drive systems can lead to dramatic bearing failure. The presentation will review the cause-and-effect chains of these currents, measuring and modeling techniques, and give a survey of the different mitigation techniques that are available. Furthermore, there is still a significant gap of knowledge with respect to the "critical bearing current load" that will lead to bearing failure. The tutorial will also provide an overview of recent activities targeting this question.
Biography - Annette Muetze is a full professor at Graz University of Technology in Graz, Austria, where she heads the Institute for Electric Drives and Machines. She received the Dr.-Ing. degree in electrical engineering from Darmstadt University of Technology in 2004 for her work on inverter-induced bearing currents and has since continued to work on various questions related to this topic. Prior to joining Graz, she worked at the University of Wisconsin-Madison, Madison, US, and at the University of Warwick in the UK. She is a currently one of the four officers of the IEEE Industry Application Society Industrial Drives Committee and Awards Chair of the IEEE 3rd Energy Conversion Conference and Exhibition (ECCE 2011).
Tutorial 2 - Technologies for Machine Condition Monitoring
Ing. Ludovico Menozzi, Business Development Manager Europe
Condition Monitoring Systems, National Instruments Italy
Topic - Condition monitoring is used by an OEM as a part of a predictive maintenance strategy for their equipment. It allows a customer to smartly, and effectively schedule maintenance on machines only when needed, rather than at set intervals or only after failure. This approach not only saves on operating and maintenance costs, but also increases production uptime. The skill is in understanding the operating parameters that indicate the degradation or the various ways that the equipment can fail, and collecting the data that the piece of equipment generates and how to meld or fuse that data together in an intelligent manner so that information is generated that’s extremely powerful and valuable.
There are many variables to consider in choosing a monitoring strategy. These include identification of typical failure modes and key machine performance indicators. A holistic approach to monitoring incorporates all system parameters to provide a complete picture of the health of the machine. On the other hand, an extreme volume of data from monitoring instruments is burdensome to evaluate and act upon.
In order to benefit from a holistic monitoring approach and to avoid data overload, smart monitors analyze and reduce at the point of data acquisition. The combination of sensor and monitoring technologies can create a smart sensor to analyze incoming sensory information and reduce it to actionable items. Measured signals, such as vibration, temperature and electrical power carry feature information describing a physical aspect of the electromechanical component where the sensor is placed. Time domain and frequency domain analysis reduces the digitized sensor signal into key features. Advanced signal processing techniques including order analysis, wavelets, Cepstrum analysis and time synchronous averaging work to address the challenges of electromechanical machines.
Tutorial 3 - Some Applications of Neural Networks in Machines and Power Systems
Prof. Ronald G. Harley, Georgia Institute of Technology, Atlanta, Georgia, US
Topic - The four main Computational Intelligence algorithms in use today are Neural Networks, Fuzzy Logic, Genetic Algorithms (GA) and Particle Swarm Optimization (PSO).The first two are used to model systems that are nonlinear, stochastic, discontinuous or where the physics of the process are too complex to describe by traditional equations. The latter two are algorithms that search for optimum solutions in a multi-dimensional solution space and are again particularly useful when systems behave in a discontinuous way where gradient descent methods do not work. Neural networks have already been applied in several cases to diagnose and predict incipient faults in machines and power systems. This tutorial will introduce the principles of neural networks and describe several applications in the field of diagnostics.
Biography - Ronald G Harley received a MScEng degree (cum laude) in electrical engineering from the University of Pretoria, South Africa in 1965, and a Ph.D. degree from London University (Imperial College) in 1969. In 1971 he was appointed to the Chair of Electrical Machines and Power Systems at the University of Natal in Durban, South Africa, and became the Head of the Department of Electrical Engineering at that university in 1983. He joined the Georgia Institute of Electrical Engineering in 1999 and is now a Regents’ Professor and the Duke Power Company Distinguished Professor at Georgia Tech in Atlanta, USA. His research interests include the dynamic behavior and condition monitoring of electric machines, motor drives, power systems and their components, and controlling them by the use of power electronics and intelligent control algorithms, wind energy, solar energy and micro grids. He has published two books, over 500 papers in refereed journals and international conferences and holds six patents. At Georgia Tech he was elected the “Outstanding Professor of 2003 in the School of Electrical and Computer Engineering”. In that same year he received an award from the IEEE-IAS-Industrial Automation Control Committee for “Recognition of Leadership and Service”. In 2005 he received The Cyril Veinott Electromechanical Energy Conversion Award from the IEEE Power Engineering Society for “Outstanding contributions to the field of electromechanical energy conversion”, and in 2009 the IEEE Richard H. Kaufmann field award with citation “For contributions to monitoring, control and optimization of electrical processes including electrical machines and power networks”. He is a Distinguished Lecturer of the IEEE Industry Application Society (IAS) and has been the Chair of the IAS Distinguished Lecturer’s program from 2003 until the end of 2010. He is currently the Treasurer of the IEEE Power Electronics Society, and Co-Chair of the IEEE PES Joint Working Group on Fault Current Contributions from Wind Plants. Dr. Harley is also a Fellow of the British IET, a Fellow of the Royal Society in South Africa, and a Member of the Academy of Science in South Africa.
Next page: Committees