Machine learning – multiple comparison values – unique result quality Deviations caused by the measurement setup, transformer state, transformer configuration, and external factors can lead to a misdiagnosis. Therefore, checking the validity and quality of the measurement results before evaluation is critical. Evaluating SFRA curves with reference data is performed by using one of the two standard algorithms, the NCEPRI algorithm (NCEPRI, North China Electric Power Research Institute) and the DLT algorithm (DLT, the Electric Power Industry Standard of the Peoples Republic of China, DL/T 911 – 2004). 19,787 SFRA curves representing over 2,000 power transformers were available to train the algorithms. The results show that artificial intelligencebased algorithms are suitable for automatic qualification and validation of SFRA measurements. Currently, the algorithms are very well suited for auxiliary purposes. Users can pre-validate their own SFRA curves based on three different classes. The measurement results qualify as OK, Investigate, and Error. This possibility enables an enormous increase in the quality of your data and brings your asset into sharper focus. Artificial intelligence Any techniques that allow machines to solve a task the way humans do Machine learning Algorithms that allow computers to learn from examples without being explicitly programmed Deep learning A subset of AI which uses models and automatically builds a hierarchy of data representations Artificial intelligence Machine learning Deep learning 42
RkJQdWJsaXNoZXIy NTkxNzY=