<p>As per the literature, the reasons for error in the profile of Manufactured Blade are changed in the profile of Wax Pattern, Distortion Allowance (Warping), Human (Operator) Error, Machine Error. Because of this, the bending of the blade is one of the dominating factors in the manufacturing considerations as it directly impacts the performance of propeller in terms of propulsion efficiency. As, the bending is unpredictable and depends on several factors, redesigning the manufacturing methods and thereby improving accuracy is an inefficient way. Traditionally, the shape healing of the blade can be carried out with hand hammers by skilled laborers. But, recovering the accuracy in the profile is still a challenge. It needs to develop the atomized post-cure techniques, which is an overlooked area over a period of time in the research of manufacturing of propellers.</p><p>The blade molding equipment developed has extensive control over the bending. The concept of the equipment is inspired by the ‘Pin-Art Board’. It has two parallel plates having no. of adjustable rods attached in a perpendicular. First, the working blade is attached and the rod position is mimicked from the surface of the blade. Then the defective blade is attached. The reformation is carried out by simply moving the parallel plates towards each other and letting the rod to press the blade at specified points of the blade. After understanding the working mechanism of the instrument, a simplified model was created to perform the numerical analysis over the blade to understand the nature of deformation. The Theoretical and numerical analysis was performed assuming the contact between the rods of the equipment and the blade is frictionless. The region of the bent propeller blade was scanned to know the deviation error. Implementing the AI tool to predict the operation points and required force per region for the blade the reformation was carried out. Also, numerous factors contribute to the effect of net spring back occurs in the metal sheet. But, because of the limitations on the availability of the literature regarding formulation to add the effect of strain hardening and Sheet preheating effects one needs to approximate the solution. To approximately predict the amount of spring-back, factors such as bending force, material properties, sheet thickness, and boundary (support) conditions are considered in the theoretical analysis and testing.</p>

Implementation of Artificial Intelligence in Bending Analysis of Propeller/Fan Blade

Paper Proceedings: https://asmedigitalcollection.asme.org/ISPS/ISPS2021/volume/84799

ASME 2021 Information Storage and Processing Systems (ISPS2021)

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.