This innovative engineering project in Japan is strategically shifting autonomy from a retrofit concept to an integral driver of the operation of new combined cycle power plants. A key question this poses is how the design and operation of future power generation assets will blend human experience garnered over an average 30 year career, with machine based information that continually learns in real time 24 x 7.
A further consideration is when, not if, will machines generate new engineering and operational design concepts, which are beyond the current human understanding of how to build and operate efficient power assets. In such cases how much will an engineer trust a machine's decision in the build process that could impact the operation of critical national infrastructure sometime in the future?
Instead of teaching AI to play chess based on analysis of thousands of chess matches, we teach the AI to ‘talk power plant,'