This study has examined some of the AI-based CFD approaches that have gained applications relative to the setup and solution of CFD problems. Some of the merits associated with the perceived automation of CFD tasks include reductions in the CFD solution turnaround time, consistency in application, the distribution, preservation, and codification of expertise, and relief from tedium. These limitations have led to increasing research on AI with the aim of ensuring that some of the CFD-related tasks that humans perform currently are automated.
AI DESIGN TECHNOLOGY FOR AIRFOIL GENERATOR CODE
During the establishment of CFD solutions, most of the reasoning used during intermediate solution assessment, graphical display, code execution, data format, parameter adjustment, discretization, and geometry definition has proved to be a rate-limiting step, that requires some expertise or experience, and is sensitive or prone to error. Despite these efforts, there remains a traditional labor separation between computers and humans, whereby computers play the role of number computation while humans participate in decision making. Particularly, CFD problem decision making by humans (regarding solution interpretation and problem setup) has been enhanced through the use of high-speed color graphics, while the computational part has been streamlined using improved algorithms, solutions methods, and grid generators. Imperative to highlight is that efforts aimed at enhancing the CFD methodology have examined both forms of activities. On the other hand, some CFD activities require high-speed numerical processing by computers. On one hand, some CFD activities require human perception, reasoning, and knowledge. In CFD practice and research, all phases constitute two broad categories of activities. Given this dilemma, it becomes important to examine some of the AI/CFD or AI-based CFD approaches that have been applied to different CFD tasks, as well as some of the factors affecting the success of the perceived approaches.
However, some scholarly observations contend that when CFD tasks are formalized or understood poorly, the application of AI technology leads to a large investment of effort and long system development times, with payoff unguaranteed. This increasing trend has been motivated by the documentation that AI/CFD systems are better placed and promising relative to their successful application to some of the well-formulated CFD problems that require pre-enumerated solution selection or classification. In the past few decades, several research attempts have strived to utilize artificial intelligence (AI) in solving computational fluid dynamics (CFDs)-related problems translating into AI/CFD systems.
0 kommentar(er)
