Gathering the requirement is the vital steps for every successful quality software. Requirement Engineering is the key role for gathering the requirement. The good quality software development require useful data requirement. In recent Software Engineering achieve the data centric with the involvement of big data, artificial intelligence (AI) and machine learning. The most of data gathered from different sources with the evolution of technology, social media and other sources. There are many factors while gathering the requirement to produce the product with good quality. This Paper highlights and extends the research scope of existing requirement engineering to meet the new challenges of requirement clusterization and increase the productivity of product in regards to customer requirement. There is need of applying classification and clustering technique to form requirement clusterization.
The most common diagnosis method for transformer faults is dissolved gas analysis (DGA). The transformer insulation (oil/paper) under abnormal electrical, mechanical or thermal stress dissociates to produce small quantities of gases. These gases are analysed for their composition, using various conventional methods, to detect the fault type in power transformers. In case of multiple fault diagnosis by DGA, the mixing of different characteristic gases results in a ratio code, which cannot be matched by the existing ratio codes, defined by various methods e.g., Rogers ratio method, Dorenberg ratio method, IEC 605999 method etc. To overcome this major drawback of DGA, the transformer diagnostics based on expert systems has been developed. This paper proposes different neural network architectures and fuzzy logic technique, as a diagnostic tool for the fault detection of transformer, using dissolved gas analysis method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.