Abstract:
In today’s world, many experts view nuclear power as an eco-friendly energy source producing the smallest possible amounts of harmful emissions into the environment. However, this is not quite the case: uranium is a non-renewable resource, nuclear power plants (NPPs) produce waste, and the disasters that took place at the Chornobyl NPP in 1986 and the Fukushima NPP in 2011 have caused harm not only to the environment by polluting the air and water resources with nuclear substances but also to human lives and health. This is why the risk of error at NPPs must be reduced to zero. Digitalization, which has a special role in implementing global sustainable development goals specifically, could be helpful in this regard. The research aims to analyze the digitalization process of the nuclear industry as a way to improve the safety, efficiency, and performance of NPPs, which helps monitor and control operations in real-time, enhance engineering, operating, and production processes providing clients with various environmental and social benefits, and facilitate the implementation of sustainable development goals. The research concludes that big data technologies help reduce the risk of error when analyzing important indicators by 25%: installation of sensors at the core units of a nuclear power plant makes it possible to control the condition of equipment and monitor the life cycle of the system. Digital twins can be used as training simulators for operators and as simulation environments for engineering experiments and research. Virtual NPPs will be useful in simulating any mode of operation at power units, from normal operations to complex emergencies, thereby preventing incidents and reducing costs. Virtual reality technologies are indispensable in training engineers and specialists whose qualifications and actions are crucial to the safety of NPPs. VR models offer an opportunity to β€_x009c_visitβ€_x009d_ an NPP, take a look at the equipment and learn to work with turbines, which is conducive to making an informed decision if an emergency occurs in reality. Predictive analytics enable the collation and program analysis of all incoming data to generate predictions regarding equipment operation and possible malfunctions. This information can be used to perform preventive maintenance and anticipate abnormal situations. Predictive analysis helps compile and study large amounts of information to detect and diagnose existing and future defects. The results obtained can be used by NPPs and other industries that only start integrating digital technologies into their activities. Β© The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.
