Special Issue of Journal of GPPS
We would like to draw your attention to a forthcoming GPPS Journal special issue entitled ‘Data-driven Modelling and High Fidelity Modelling’. This was initiated against the backdrop of both the rapid advances in Artificial Intelligence (AI) and Machine Learning (ML) in many fields globally in general, and the more specific needs and challenges in gas turbine technology development in particular.
The contributors to the special issue include: Dr. V. Michelassi (Baker Hughes), Dr. J. Ling (Citrine Informatics), Prof. G. Iaccarino (Stanford U.), Prof. R. Sandberg (Melbourne U.), Prof. G. Pullan (Cambridge U.), Prof. J. Seume (Hannover U.), Prof. C. Hirsch (NUMECA). The papers selected should be indicative of the recent advances in design and verification methods that take advantage of the continuous growth of computational resources, the availability of large data sets, and the evolution of methods and algorithms. The new methods and new understanding gained should offer new opportunities to unlock further improvements and the new technology development outside conventional design spaces (e.g. new fuels, interface with renewables or carbon avoidance, reduction, capture and sequestration etc). These should also potentially allow to address the two key challenges rotating machinery will face in the next decades. First, the rapidly changing scenario of power generation and aircraft propulsion requires ever shorter time of design-to-market without compromising performance, availability, and cost. Second, the foreseeable future will see a further step-change in technology and opportunities that call for significant extension of the design space and decisive nonconventional steps away from currently comfort design zones.
The production of these papers is currently under way and the publication of the special issue (open online with free access) is expected in April/May 2021. Please visit the Journal website (https://journal.gpps.global/special issue) in time.
Professor L. He (Editor, Journal of GPPS)