As the shipbuilding industry is an engineering-to-order industry, different types of products are manufactured according to customer requests, and each product goes through different processes and workshops. During the shipbuilding process, if the product is not able to go directly to the subsequent process due to physical constraints of workshop, it temporarily waits in a stockyard. Since the waiting process involves unpredictable circumstances, plans regarding time and space cannot be established in advance. Therefore, unnecessary movement often occurs when ship blocks enter or depart from the stockyard. In this study, a reinforcement learning approach was proposed to minimise rearrangement in such circumstances. For this purpose, an environment in which blocks are arranged and rearranged was defined. Rewards based on the simplified rules were logically defined, and simulation was performed for quantitative evaluation using the proposed reinforcement learning algorithm. This algorithm was verified using an example model derived from actual data from a shipyard. The method proposed in this study can be used not only to the arrangement problem of ship block stockyards but also to the various arrangement and allocation problems or logistics problems in the manufacturing industry.

Curved hull plate forming, the process of forming a flat plate into a curved surface that can fit into the outer shell of a ship’s hull, can be achieved through either cold or thermal forming processes, with the latter processes further subcategorizable into line or triangle heating. The appropriate forming process is determined from the plate shape and surface classification, which must be determined in advance to establish a precise production plan. In this study, an algorithm to extract two-dimensional features of constant size from three-dimensional design information was developed to enable the application of machine and deep learning technologies to hull plates with arbitrary polygonal shapes. Several candidate classifiers were implemented by applying learning algorithms to datasets comprising calculated features and labels corresponding to various hull plate types, with the performance of each classifier evaluated using cross-validation. A classifier applying a convolution neural network as a deep learning technology was found to have the highest prediction accuracy, which exceeded the accuracies obtained in previous hull plate classification studies. The results of this study demonstrate that it is possible to automatically classify hull plates with high accuracy using deep learning technologies and that a perfect level of classification accuracy can be approached by obtaining further plate data.

No abstract

No abstract

3-D templates are produced to evaluate completeness of the shell plates during the forming process, which is an essential step for the ship production. They are mostly produced in advance during the detail/production design stage, but occasionally they are requested by the shell plate forming department, because it is impossible to predict accurately the necessities of them at the design stage. This results in a huge loss of man-hour and a bottleneck. In order to resolve this issue while reducing the dependence on other department, the process of manufacturing the 3-D templates needs to be automated. Therefore, this study proposes an automatic system that calculates the manufacturing information of the 3-D templates with only geometric information of the shell plates. The system considers the thickness and the cutting method of the parts of the 3-D templates and some options are provided to reflect the intention of the worker.