Dr Sandip Bordoloi, Associate Professor, Department of Electrical Engineering, GIMT, Guwahati.
Electrical engineers work on a wide range of components, devices, machines, and systems, from tiny microchips to huge power station generators. Electrical systems, many a times, are so complex that they require expert systems to monitor and supervise them. Such supervisory systems may comprise high-end computers that use complex algorithms and software to regulate the flow of electrical energy obtained from different sources to domestic and industrial consumers.
A modern expert system such as Artificial Intelligence can pave the way to leverage data for ‘data interpretation’ and ‘decision-making’. The application of Artificial Intelligence technology on power systems is an active area of research and significant success has been achieved in this area to date. So, what is Artificial Intelligence and how can it be associated with Electrical Engineering? “Artificial Intelligence (AI) is a wide-ranging branch of computer science concerned with building smart machines capable of performing tasks that typically require human intelligence”. Recent progress in areas like machine learning, big data analysis, and natural language processing has affected almost every area in academics, industry and business and, therefore, engineering is no exception. AI is the simulation of the process of data interaction of human thinking in a machine, so as to produce a smart machine, which can think like a human being to provide a problem, respond and deal with the problem. Machine learning and big data analysis can help leverage AI to build and optimise electrical systems by providing AI technology with new data inputs for interpretation and decision-making. In addition, harnessing AI’s potential may reveal chances of boosting system performance while addressing problems more efficiently.
AI is used to program machines to learn and mimic the actions of humans. These machines are able to learn with experience and perform human-like tasks. For years, researchers, engineers and scientists have been fascinated with the concept of how machines can be taught to replicate tasks ordinarily done by humans. Machines can now be fed with a huge amount of data to make them more ‘Artificially Intelligent’. The concept of AI is not new. Different forms of intelligent systems have been incorporated in Electrical Engineering for a long time, some of which are discussed below:
Expert systems: An expert system (ES) is a software system that captures human expertise for supporting decision-making. These systems are useful for online operations in the control field because they incorporate symbolic and rule-based knowledge, in the form of if-then rules to solve problems. The expert system consists of knowledge base, database, reasoning machine, interpretation mechanism, knowledge acquisition and user interface.
Fuzzy logic control systems: “Fuzzy logic is a basic control system that relies on the degrees of state of the input and the output depends on the state of the input and rate of change of this state”. The fuzzy control system uses a rule-based system for how machines will respond to inputs that account for a continuum of possible conditions, rather than straightforward binary rules.