Resistance and Trim Modeling of a Systematic Planing Hull Series 62 (with 12.5 degrees, 25 degrees, and 30 degrees Deadrise Angles) Using Artificial Neural Networks, Part 2: Mathematical Models

Abstract

Recent advances in high-speed computing, combined with the emergence of artificial neural network (ANN) techniques for the analysis of large data sets, has enabled researchers to provide the design community with higher-resolution mathematical models (MMs) for existing test data. Presently, one of the most popular planing hull prediction methods for resistance and trim are based on regressions of the Series 62 database. New MMs developed here address two major shortcomings of the original approaches; first, the equations are now continuous functions of volumetric Froude number (rather than separate regressions for each speed), and second, MM for trim is much more accurate, enabling designers to identify the double hump in trim that is associated with dynamic instabilities at higher speeds. This work describes the derivation of MMs for calm water resistance and running trim angle corresponding to volume Froude numbers of 1.0-4.0, and includes not only the original David Taylor Model Basin Series 62 data for 12.5 degrees deadrise, but also the later extensions made by Delft University of Technology, including 25 degrees and 30 degrees deadrise. Part 1 of this research, published separately, explains the streamlining of the foundational database-how outliers are identified, and methods to provide a database from which stable MM can be developed. The present article, Part 2, deals with the derivation of the actual mathematical model. Two ANN techniques were used, with single output, which has been applied to similar problems in the past, and with multiple output, which is a new approach to the problem. The results of the two different methods, both developing satisfactory models, are discussed and compared.