Final

Optimising Windmill Tower Turbine Using Generative AI.

[Audio] This presentation discusses the use of Generative AI in optimizing windmill tower turbines. The study was conducted by Nikhil S Goudar, Niranjan N Hiremath, and Harshavardhan J Patil, under the guidance of Nagraj Ekbote and Geeresha C at KLE Technological University. The study presents an AI-driven framework that integrates Generative AI with advanced engineering simulation tools such as ANSYS and SolidWorks. This system is capable of exploring and analyzing hundreds of flange design variants under diverse loading conditions. Through modal and structural analyses, four design configurations were developed and evaluated. Among them, Design 4, which features a hollow-flange geometry, demonstrated superior performance in terms of lightweight construction, high stiffness, uniform stress distribution, and an enhanced natural frequency. The fusion of AI-based generative modeling with physics-informed simulation has resulted in a significant advancement towards fully automated, data-driven, and high-precision engineering for renewable energy systems. This will enable faster, cost-effective, and sustainable turbine development. Thank you for your attention and we hope you will find this presentation informative as we discuss the use of Generative AI in optimizing windmill tower turbines in greater detail..

[Audio] The demand for sustainable energy is at an all-time high in today's rapidly evolving world. To meet this demand, we must make our energy sources more efficient and environmentally friendly, which is where Generative AI comes in. This innovative technology has the potential to significantly optimize windmill tower turbines, making them more efficient, lightweight, and sustainable. The problem we are trying to solve is the time-consuming and limited design process for wind turbines. The traditional trial-and-error approach results in sub-optimal designs with excess material usage and reduced efficiency. Our challenge is to find a more efficient and effective design process for wind turbine towers, and that's where Generative AI comes into the picture. By using models like ChatGPT, Gemini, and DeepSeek, integrated with engineering simulation tools such as ANSYS and SolidWorks, we can automate and speed up the optimization process. This allows us to explore hundreds of structural variants at a rapid pace, learning from performance feedback to identify the most efficient geometries. The end result is a high-stiffness wind turbine tower design with a superior strength-to-weight ratio, lower material consumption, and increased operational reliability. This design process not only saves time and resources but also reduces operational costs and contributes to a more sustainable future. With the help of this groundbreaking research, we can make a significant impact in the field of wind energy. This project was presented by Nikhil S Goudar, Niranjan N Hiremath, and Harshavardhan J Patil under the guidance of Nagraj Ekbote and Geeresha C at KLE Technological University..

[Audio] Slide 4 discussed the use of Generative AI in optimizing windmill tower turbines. The research team, led by Nikhil S Goudar, Niranjan N Hiremath, and Harshavardhan J Patil, and guided by Nagraj Ekbote and Geeresha C, presented their findings at KLE Technological University. The focus of their study was the optimization of the turbine hub flange, a critical component that connects the main shaft to the blade system. Their research showed that the conventional solid flange design added unnecessary mass and limited dynamic efficiency. To improve wind turbine performance, they redesigned the flange to find an optimal balance between weight, stiffness, and vibration resistance. This was achieved through a geometry-driven refinement process and AI-assisted simulation, resulting in a lightweight structure without compromising mechanical integrity. The team's key design objectives were weight optimization, structural performance enhancement, and vibration and fatigue improvement. Through this approach, they believe they can significantly enhance the efficiency and reliability of wind turbine systems..

[Audio] "On Slide 5, we will be discussing our various designs for windmill tower turbines. First, we have Design 1, the base model, which is a standard wind turbine flange made of structural steel with no geometric modifications. While it provides reliable reference values, it may not be the most efficient design. Design 2, our improved version, features an added secondary flange for increased stiffness. This design improves load distribution and reduces deformation while maintaining the same dimensions. Design 3 is a hollow structural steel flange with the original dimensions, resulting in reduced weight and improved efficiency compared to solid configurations. Finally, we have Design 1 as our baseline design, which offers high strength but is heavier and has moderate deformation. Moving on, our team at KLE Technological University, led by Nagraj Ekbote and Geeresha C, has been tirelessly researching the use of Generative AI to optimize windmill tower turbines. We hope that our findings will contribute to the advancement of renewable energy technology. We will also be introducing Design 4 in the future. Thank you for your attention and we look forward to continuing our discussion on this topic..

[Audio] Slide 6 out of 12 discusses the simulation methodology used to optimize windmill tower turbines with Generative AI. Two software tools, ANSYS and SolidWorks, were utilized for 3D modeling and finite element analysis, providing critical insight into the tower's structural behavior. The analysis was divided into Modal and Structural analysis, determining natural frequencies, vibration modes, deformation, stress distribution, and stiffness. To mimic real-world conditions, Free-Free and Fixed-Free boundary conditions were applied to the tower. Static loads ranging from 15 to 50 kg were used to simulate wind-induced stresses and analyze the tower's behavior. Structural Steel was chosen as the material, with specific parameters set for Young's Modulus, density, and Poisson's Ratio. The tower's geometry and mesh were also carefully selected for accurate and stable results, with solver settings optimized for precision and computational efficiency. This comprehensive simulation methodology allowed for a thorough understanding of windmill tower behavior, furthering the advancements in Generative AI design and increasing efficiency and sustainability in wind energy systems..

[Audio] Our team has made significant progress in the field of windmill tower turbines using Generative AI. Through initial research, we established baseline metrics for the dynamic behavior of the tower, with a measured natural frequency of 2.7143 Hz and maximum deformation of 0.20011 mm under test loads. However, further analysis showed that the mass distribution was inefficient. To improve upon this, we maintained the base geometry with a solid flange, resulting in a natural frequency of 2.1743 Hz and a deformation of 0.20011 mm. However, the weight was still high, resulting in excess inertia and moderate deflection. In our next iteration, we added a flange that significantly improved load transfer and stiffness, resulting in a decreased natural frequency of 1.9484 Hz and a reduction in deformation to 0.11424 mm. However, this also increased the mass compared to a hollow configuration. To address this, we hollowed out the flange, resulting in a decreased natural frequency of 1.1751 Hz and a reduction in deformation to 0.09932 mm. This led to weight savings and improved efficiency, as well as lower stresses under operational loading. Our team will continue to refine and optimize the windmill tower turbines using Generative AI and we look forward to sharing our progress with you..

[Audio] Our team, consisting of Nikhil S Goudar, Niranjan N Hiremath, and Harshavardhan J Patil, conducted research under the guidance of Nagraj Ekbote and Geeresha C at KLE Technological University. We are pleased to reveal that our findings have shown significant improvements over the base model. Design 4 has demonstrated a superior combination of low deformation and optimized natural frequency, indicating an excellent balance of stiffness and weight. These enhancements have resulted in a more efficient and effective windmill tower turbine. We attribute these improvements to our use of Generative AI, which has played a crucial role in the design process through advanced algorithms and data-driven techniques. Moving forward, we are excited to see the continued impact of this technology in revolutionizing the renewable energy industry. Let's now move to our next slide and explore the potential impact of this project..

[Audio] We are now discussing the results of our research and testing regarding the use of Generative AI in optimizing windmill tower turbines. We have included an error histogram to compare the performance of our Generative AI model to traditional methods. The blue bars represent errors in our model, while the orange bars represent errors in traditional methods. Our model shows significantly lower errors, indicating higher accuracy and efficiency. Additionally, we have a performance plot showing that our model outperforms traditional methods, with the best result achieved at epoch. This data demonstrates the effectiveness of Generative AI in optimizing windmill tower turbines, providing not only better accuracy and efficiency, but also the potential for continuous improvement over time. Special thanks to our team and mentors at KLE Technological University for their hard work and dedication. Thank you for your attention, and we will now move on to our next slide..

[Audio] The modal analysis results for a 50 kg load show that the fixed and free frequencies for the windmill tower turbines have slightly changed compared to the previous 30 kg load results. This is because the added weight of the load affects the overall vibration and frequency of the tower. However, there is still a significant decrease in the fixed frequency, indicating that the use of Generative AI has successfully optimized the tower's design and reduced its vibrations. The fixed frequency ranges from 1.29 to 1.9648 Hz, while the free frequency ranges from 12.616 to 17.5 Hz, providing a larger gap between the two frequencies. This suggests a higher level of stability and decreased likelihood of resonance. This is a great achievement for our team, as our main goal was to minimize vibrations and improve the overall performance of windmill tower turbines. With the help of Generative AI, we were able to achieve this. These results were obtained through extensive research and testing under the guidance of our mentors, Nagraj Ekbote and Geeresha C, and presented by Nikhil S Goudar, Niranjan N Hiremath, and Harshavardhan J Patil at KLE Technological University. We hope that our findings will contribute to the advancement of wind energy technology and further promote efficient and sustainable energy solutions. We welcome any questions or comments you may have as we continue to strive for innovation and make a positive impact on the environment..

[Audio] Design 4, featuring a hollow-flange configuration, has proven to be the optimal solution for windmill tower turbines through the use of Generative AI. Our team integrated AI-driven design and advanced simulation, utilizing this design to achieve the best overall balance of performance characteristics. This lightweight structure boasts reduced material usage while maintaining strength, allowing it to withstand heavy loads and harsh weather conditions. The stiffness and stability of Design 4 ensure smooth and consistent operation without significant deformations. The durability has also been improved, extending the operational lifespan of wind turbines utilizing this design and providing clean and renewable energy for years to come. Quantitatively, Design 4 achieved a natural frequency of 1.9484 Hz and a maximum deformation of 0.11424 mm, demonstrating a well-balanced performance with minimal vibration. Through this optimized design, our team has showcased the potential of AI-assisted engineering in delivering lighter, stronger, and more efficient wind turbine components. This is just one example of how Generative AI can improve and optimize processes and designs. We would like to thank our team and mentors at KLE Technological University for their hard work and dedication in achieving this successful design. As we conclude our presentation, we hope it has sparked your interest in the use of Generative AI in the engineering field..

Thank You.