This study proposes methods to improve the performance of Iterative Closest Point (ICP) algorithm. This algorithm is used in many areas, such as the inspection of fabricated parts. The field of inspection is very necessary to ensure the quality of the production. The inspection of manufactured parts consists of automatically comparing their CAD model with their point clouds. The comparison of these two models makes it possible to conclude whether a manufactured part conforms to its theoretical model defined during its design. In this paper, the proposed control method is based on the ICP algorithm. The principle of this algorithm is to find the optimal rigid transformation to readjust the point clouds (measured on the real part) on the manufactured part. Many variants of ICP algorithm are proposed in this paper. They reduce errors and improve inspection, quality of machined parts. A comparison of their efficiencies on the purpose of improving performance and accelerating the convergence speed of the ICP algorithm is performed.