Bayesian optimization for multi-screw archimedes turbine design

安大略省德里的Bluestreak Equipment正在开发阿基米德螺杆水力发电机(ASG)，可用于安大略省水道沿线数千个低水头(1-10米)的地点。在过去的十年里，欧洲已经安装了数百个ASG，还有更多正在开发中。与其他水轮机相比，ASG在商业上具有竞争力，对环境的影响非常小，包括对鱼类的影响。在过去的六年里，Bluestreak研发了他们的阿基米德螺杆发电机技术，并成功地安装了北美第一座并网发电的阿基米德螺杆水电站。他们目前正在将他们的ASG系统商业化，并在不同的计划阶段还有几个。Bluestreak和Guelph大学的David Lubitz教授开发并验证了一种改进的工程模型，该模型可以可靠地预测特定阿基米德螺杆系统的功率输出。该模型可用于迭代优化特定地点单个阿基米德螺杆发电机的内部收益率，是Bluestreak在微水能领域的业务优势的关键部分。*Guelph大学的Graham Taylor博士的研究团队通过Engage和Engage Plus项目与Bluestreak合作，通过基于贝叶斯优化的解决方案取代费力的手动参数调整，以找到最佳地点特定配置。此后，Bluestreak开始考虑在每个站点安装多个螺丝。因此，这两年的CRD旨在将目前的框架扩展到多个阿基米德螺杆涡轮机(AST)同时优化的实际情况。我们还将改进性能模型和优化器(与单螺杆和多螺杆相关)。该项目旨在使Bluestreak的系统更具竞争力，同时推进工程设计的全球优化的最先进水平。

Bluestreak Equipment, of Delhi, Ontario, is developing Archimedes screw hydro generators (ASGs) that could be utilized at thousands of low head (1-10m) sites along waterways just in Ontario. Several hundred ASGs have been installed in Europe in the past decade, with more in development. ASGs are commercially competitive with other hydro turbines, with very low environmental impacts, including on fish. In the past six years, Bluestreak researched and developed their Archimedes screw generator technology, and successfully installed the first grid-connected Archimedes screw hydro plant in North America. They currently are commercializing their ASG system and have several more in various stages of planning. Bluestreak and Prof. David Lubitz (University of Guelph) have developed and validated a refined engineering model that can reliably predict the power output of a specified Archimedes screw system. The model can be used iteratively to optimize the IRR of a single Archimedes screw generator for a specific site, and is a key part of Bluestreak's business advantage in the microhydro field.****Dr. Graham Taylor's research team at the University of Guelph collaborated with Bluestreak through Engage and Engage Plus projects to replace the laborious laborious manual tuning of parameters to find an optimal site-specific configuration with a Bayesian Optimization-based solution. Bluestreak has since moved to consider multiple screws installed per site. Therefore, this 2 year CRD aims to extend the current framework to the practical case where multiple Archimedes screw turbines (ASTs) are optimized simultaneously. We will also develop improvements to the performance model and optimizers (relevant to both single- and multi-screw). The project aims to make Bluestreak's system more competitive while advancing the state-of-the-art in global optimization for engineering design.******