Ontology based knowledge extraction for shipyard fabrication workshop reports

In this paper, a method to extract knowledge from a set of surveyors’ reports is proposed. Many surveyors from shipping companies are working in shipyards to improve the quality and to meet requirements of the ship owner. At present, the reports from surveyors are used only for managing the status of problems of the product. The proposed method here has three steps. First, the description field of the reports which contains information about some trouble is summarized in a pair of a component name and a trouble name in the failure database; this is made possible through text-processing technology. Second, synonymous component and trouble names are consolidated into normalized terms using synonym ontology to prepare this information for statistical analysis. The synonym ontology is developed prior to this procedure. The system evaluates frequent trouble records by classifying the records using component and process ontology. In the last step, the designers extract knowledge from the information generated by the system. The results illustrate common design problems, and the method is proved to be useful.