Digital Protective Schemes for Power Transformer

India is a leading country and its economy grows day by day by attracting foreign direct investments (FDI). Production, manufacturing, industrial, software, and all other business depends on reliable electricity supply with a slogan of “without power-no business”, shows the importance of reliable power supply. The protection of the power system is a very sensitive and burning issue due to huge expansion, complexity, and deregulation. Future power reliability with growth in power generation, expansion, and improvement as per nation demand is the main challenge for India.

This division presents a new Current Transformer (CT) saturation detection and compensation algorithm. The proposed algorithm depends on a saturation detection index (Dn) which is derived using derivatives of current signals and Newton’s backward difference formulas.

Conventional protection schemes of a power transformer may operate during abnormalities such as Inrush condition, CT saturation during an external fault, and high resistance internal fault conditions.

Due to the presence of Distribution Generation (DG), the power system becomes more complicated and stability of power is the main challenging task. Saturation of Current Transformer (CT) imposes a great dilemma on differential relaying scheme.

This editorial presents a new scheme, based on Relevance Vector Machine (RVM) as a fault classifier. The developed algorithm is assessed by simulating various disorders on 345 MVA, 400/220 kV transformer in PSCAD/EMTDC^TM software, and also on prototype model with 2 kVA, 230/110 V multi tapping transformer.

Various unwanted phenomena that are taken place in the transformer may occasionally mal-operate selected fault classification based protective schemes. Hence, it is necessary to discriminate internal fault from external abnormal conditions for unit protection of power transformer. This paper presents a new Hierarchical Ensemble Extreme Learning Machine (HE-ELM) based classifier technique to identify faults in & out of the transformer. The component ELMs is structured hierarchically to improve its fault data classification accuracy. The developed algorithm is evaluated by simulating multiple disorders on 100 MVA, 132/220 kV transformer with the help of PSCAD software. DWT is used to extract features from acquired current signals from the transformer. The feature vector formed after the extraction process is fed to the HE-ELM algorithm for data classification. The fault discrimination accuracy of the HE-ELM technique is 99.91%. This shows its effectiveness concerning other classifier techniques. Moreover, the developed algorithm is successfully tested on hardware prototype in a laboratory environment under various inrush and fault conditions using a Cortex M4 microcontroller (STM32F407) with maximum identification time of 27 ms. The proposed HE-ELM technique is compared with existing SVM, PNN, and ELM techniques for identical fault data. Results demonstrate that HE-ELM outperforms than existing schemes in the cross-domain recognition task.

The power transformer is one of the most important equipment in the grid to reliably and efficiently transmit power to the consumers. Asset management and protection are the best concepts for enlargement of transformer lifespan as well as to increase the grid reliability. This article presents the electrical and non-electrical parameter based power transformer monitoring and protection.