Monitoring, diagnostic and prognostic methods - IV
Chair: Dr. Yun-Ho SEO (Korea Institute of Machinery and Materials)
Maintenance Analytics, industrial data science and virtual commissioning Prof. Diego GALAR (Luleå University of Technology)
Industrial systems are complex with respect to technology and operations with involvement in a wide range of human actors, organizations and technical solutions. For the operations and control of such complex environments, a viable solution is to apply intelligent computerized systems, such as computerized control systems, or advanced monitoring and diagnostic systems. Moreover, assets cannot compromise the safety of the users by applying operation and maintenance activities. Industry 4.0 is a term that describes the fourth generation of industrial activity which is enabled by smart systems and Internet-based solutions. Two of the characteristic features of Industry 4.0 are computerization by utilizing cyber-physical systems and intelligent factories that are based on the concept of "internet of things". Maintenance is one of the application areas, referred to as maintenance 4.0, in form of self-learning and smart systems that predicts failure, makes diagnosis and triggers maintenance by making use of “internet of things”.
Thus, for complex assets, much information needs to be captured and mined to assess the overall condition of the whole system including the one from design and manufacturing which obviously contains the physical knowledge. Therefore the integration of asset information during the entire lifecycle is required to get an accurate health assessment of the whole system, and determine the probability of a shutdown or slowdown avoiding black swans and other unexpected or unknown asset behaviors.
Moreover, the asset data are not only huge but often dispersed across independent systems that are difficult to access, fuse and mine due to disparate nature and granularity. If the data from these independent systems are combined into a common correlated data source, these new sets of information will add value to the individual data sources.
This talk will discuss the possibilities that lie within applying the maintenance analytics concept by the means of virtualization i.e virtual commissioning of the assets through data fusion and integration from a systems perspective.
A Self-Organization Strategy for Unmanned Autonomous Systems Mr. Benjamin LEE, Sehwan OH, Michael BALCHANOS and George VACHTSEVANOS (Georgia Institute of Technology)
Complex systems are constructed from multiple subsystems and components with each serving incrementally specific tasks, where the “emergent” system behavior cannot be deduced from the behaviors of the individual parts. The key requirement of real-life complex systems is the ability to adjust/compensate rapidly to sudden and extreme external or internal failure modes, so it is important to build a self-organizing control system with high confidence to achieve on-line self-organization from the component to the mission level. Therefore, detailed and accurate knowledge of system behaviors, as an essential part of the self-organization strategy, is paramount in complex system control. This paper presents a self-organizing control strategy that incorporates both situational awareness and fault impact compensation for a resilient unmanned autonomous system (UAS). Some methods to understand system behavior are data acquisition, system modeling, and proper construction of performance metrics, which includes a policy to deal with changing system condition and success criteria to evaluate the performance of the policy action. The purpose of system data acquisition is to obtain the key variables and parameters. Such data can be obtained through various system modeling platforms, including MATLAB/Simulink, Gazebo/ROS, Markov Chain Modeling, etc. The enabling technologies begin with graph spectral and epidemic spreading modeling tools to represent the system behaviors under normal and faulty conditions; a Markov Decision Process as the basic self-organization module follows it. Decision-making is based on the current state only, regardless of the system’s operation history in accordance with the Markovian property. A typical unmanned autonomous ground vehicle – the hexapod – is employed as the testbed for the development and validation of the self-organizing strategy. Simulation results show the efficacy of the approach.
System Health Monitoring of Wind Turbines Using SCADA Data and Gaussian Mixture Models Mr. Akihisa YASUDA, Jun OGATA, Masahiro MURAKAWA, Hiroyuki MORIKAWA and Makoto IIDA (The University of Tokyo, National Institute of Advanced Industrial Science and Technology)
Wind turbines are the major driving force to produce renewable energy, but there is a strong need of reducing the costs of operation and maintenance. To detect anomalies of wind turbines, this paper proposes a method which uses the data collected by Supervisory Control And Data Acquisition (SCADA) system and is based upon building the normal behavior model of wind turbines. This is achieved by using supervised data and Gaussian mixture models with filtering SCADA data from the macroscopic point of view. The method is validated with SCADA data collected from actual 2-MW wind turbines. The results show the potential of detecting anomalies and the effectiveness of filtering conditions for building the model.
Parameter Estimation Using Particle Filter for Induction Machines under Inter-Turn Fault Mr. Viet Hung NGUYEN, Danwei WANG, Jeevanand SESHADRINATH, Abhisek UKIL, Viswanathan VAIYAPURI and Sivakumar NADARAJAN (Nanyang Technological University, Rolls-Royce Singapore Pte. Ltd.)
Parameter estimation has found its applications in various domains. In this paper, it is applied to fault severity estimation. A method, using particle filter approach, for estimating unknown fault parameters in stator winding inter-turn short, is firstly proposed. These parameters are insulation resistance and percentage of shorted turns. The method uses only measurements of stator voltages and currents. In order to effectively estimate the parameters, a multiple-model approach is exploited. A sequence components-based approach is applied to derive an equality constraint on the magnitude of a state variable, which works as an additional information for estimation algorithm based on state-state model. Additionally, the variance reduction technique is applied to increase the accuracy of the method.