Application of Data Analytics for Defect Detection in Power Systems
Data analytics are now playing a more important role in the modern industrial systems. Driven by the development of information and communication technology, an information layer is now added to the conventional electricity transmission and distribution network for data collection, storage and analysis with the help of wide installation of smart meters and sensors. The characterizations of big data, smart grids as well as huge amount of data collection are firstly discussed as a prelude to illustrating the motivation and potential advantages of implementing advanced data analytics in smart grids.
Efficient and valuable strategies provided by large amount of available data are urgently needed for a sustainable electricity system that includes smart grid technologies and very complex power system situations. Big Data technologies including Big Data management and utilization based on increasingly collected data from every component of the power grid are crucial for the successful deployment and monitoring of the system. This paper reviews the key technologies of Big Data management and intelligent machine learning methods for complex power systems. Based on a comprehensive study of power system and Big Data, several challenges are summarized to unlock the potential of Big Data technology in the application of smart grid. This paper proposed a modified and optimized structure of the Big Data processing platform according to the power data sources and different structures. Numerous open-sourced Big Data analytical tools and software are integrated as modules of the analytic engine, and self-developed advanced algorithms are also designed. The proposed framework comprises a data interface, a Big Data management, analytic engine as well as the applications, and display module.
Through the “e” of eMaintenance, the pertinent data, information, knowledge and intelligence (D/I/K/I) become available and usable at the right place and at the right time to make the right maintenance decisions all along the asset life cycle (Levrat et al. 2008). This is in line with the purpose of Big Data analytics, which is to extract information, knowledge, and wisdom from Big Data. Although applying Big Data analytics to maintenance decision-making seems promising, the collected data tend to be high-dimensional, fast-flowing, unstructured, heterogeneous and complex (as will be detailed in Chapter 2) (Zhang & Karim 2014), thus posing significant challenges to existing data processing and analysis techniques. New forms of methods and technologies are required to analyse and process these data. This need has motivated the development of Big Data analytics in this thesis. To cite (Jagadish et al. 2014): “While the potential benefits of Big Data are real and significant, and some initial successes have already been achieved, there remain many technical challenges that must be addressed to fully realize this potential.”
In essence, despite the fact that deep learning algorithms require a large dataset to train, they can automatically perform adaptive feature extractions on the bearing data without any prior expertise on fault characteristic frequencies or operating conditions, making them promising candidates to perform realtime bearing fault diagnostics. A comparative study is also conducted comparing the performance of many DL algorithm variants using the common CWRU bearing dataset. Finally, detailed recommendations and suggestions are provided in regards to choosing the most appropriate type of DL algorithm for specific application scenarios. Future research directions are also discussed to better facilitate the transition of DL
Zhang, L., Lin, J. and Karim, R., 2015. An Angle-based Subspace Anomaly Detection Approach to High-dimensional Data: With an Application to Industrial Fault Detection. Reliability Engineering & System Safety, 142, pp.482-497.
Levrat, E., Iung, B. & Marquez, A.C., 2008. E-maintenance: review and conceptual framework. Production Planning & Control, 19(4), pp.408–429.
Kriegel, H.-P. & Zimek, A., 2008. Angle-based outlier detection in high-dimensional data. Proceeding of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, pp.444–452.
Zhang, L., Lin, J. and Karim, R., 2016. Sliding Window-based Fault Detection from High-dimensional Data Streams. IEEE Transactions on Systems, Man, and Cybernetics: System, Published online.
Zhang, L., Lin, J. and Karim, R., 2016. Adaptive Kernel Density-based Anomaly Detection for Nonlinear Systems.