Optimal positioning of reference holes in forged turbine blades under adaptive point cloud registration based on robotic arm

The complexity of forged turbine blade machining requirements brings challenges to point cloud registration in automated hole positioning. In this paper, a weighted point cloud registration method based on directional distance function is proposed, which converts various machining requirements into adaptive weight coefficients. In addition, a coarse registration method using the global bounding box information is proposed, which fuses the multi-feature parameters into the objective function, forming a mutual feedback mechanism between the point cloud segmentation and the coarse registration, and realizing the coarse registration under two-way high-quality point clouds. Combining the two methods, a hole positioning scheme of forged turbine blade based on robot arm is developed. In the test of two typical turbine blades, the maximum homogenization improvement of the blade body machining allowance reaches 26.9 %, and the maximum improvement of the qualified rate of the machining allowance reaches 11.6 %. The proportion exceeding the lower limit of the allowable machining allowance is reduced by 19.8 % at most, and the average optimization range of about 10 % is reached when dealing with unqualified blades, which is very close to the allowable machining allowance value. The average error of blade reference hole positioning is 0.420 μm, and the maximum error is 1.652 μm, which is two orders of magnitude lower than the allowable machining accuracy. The proposed method can provide reliable data support for automatic machining of robotic arm.