Applicability of Machine Learning for Vessel Dimension Survey with a Minimum Number of Common Points

This paper presents the challenges encountered in dimensional control of ships, platforms, and offshore units. novel approach utilizes machine learning (MLP—Multilayer Perceptron Neural Network) for three-dimensional (3D) spatial coordinate transformations when only three common points are known. The proposed method was verified based on laboratory field data. main issue to provide a sufficient number valid training points. oversampling used meet this criterion. achieved results indicate equal or better accuracy were located inside adjustment array. In case where lay outside array, no improvement transformation observed. neural restores symmetry, some cases, such as study deformation engineering objects, breaks symmetry rather than restoring it.