Machine-learning-based multipoint optimization of fluidic injection parameters for improving nozzle performance
arXiv:2409.12707v2 Announce Type: replace-cross Abstract: Fluidic injection offers a promising solution to improve the performance of the overexpanded single expansion ramp nozzles (SERNs) during vehicle acceleration. However, determining the injection parameters that yield the best overall performance across multiple nozzle operating conditions remains a challenge. The gradient-based optimization method requires gradients of injection parameters at each design point, which can lead to high computational costs when using computational fluid dynamics (CFD) simulations. This paper uses a pretrai
The continuous advancements in machine learning combined with the increasing computational power make sophisticated optimization methods for complex physics problems more accessible.
This development indicates an accelerating trend of AI being applied to enhance the efficiency and performance of engineering systems, potentially leading to more fuel-efficient or higher-performing aerial and space vehicles.
The traditional, computationally intensive gradient-based optimization for fluidic injection is being supplanted by more efficient machine-learning approaches, reducing design time and cost in complex engineering fields.
- · Aerospace industry
- · Fluid dynamics researchers
- · Computational fluid dynamics software developers
- · Machine learning engineers
- · Traditional CFD optimization methods
More efficient and cost-effective design cycles for advanced nozzle technologies become possible.
Broader application of AI/ML in other complex fluid dynamics engineering challenges, accelerating innovation in related sectors.
Enhanced performance and reduced operational costs for aircraft and rockets could impact global logistics and space exploration economics.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG