Research On Modeling And Acquisition Technology Of Ship Coating Process Knowledge

Ship Coating is one of the key process technologies in shipbuilding engineering.The quality of Coating is directly related to the service life of the ship and the economic benefits of shipbuilding.In the context of China's rapid economic development and the gradual upgrading of the industrial structure,taking into account the special industrial characteristics of the ship coating industry,such as labor intensiveness,discrete links,and product customization,under the situation of rapid rise in labor costs and the disappearance of labor cost advantages,There is an urgent need to carry out new process research to replace traditional coating operations,promote automation and intelligentization of coating operations,The main research contents are as follows:(1)Analyzed the coating process of ships and classified the painting process data.Based on this,the process knowledge was defined,and the knowledge was divided into factual,decision-making,and metacognitive knowledge.A variety of knowledge modeling methods are used to realize the modeling and expression of ship coating process knowledge.Two basic methods of knowledge acquisition are introduced.Different knowledge acquisition methods are adopted for different types of knowledge to establish a knowledge base to facilitate better knowledge Store and reuse.(2)Propose a knowledge acquisition method based on principal component analysisimproved item constraint association rules.First,pre-process the painting process data,and use the principal component analysis method to reduce the dimensions to achieve a large number of multiple sources in the ship coating process.Dimension reduction processing of heterogeneous data.Then,the target data set after dimension reduction is filtered according to the leader and constraint constraints for targeted acquisition of the coating process knowledge.Then,the association rule algorithm with constraints is used to mine the rules in the coating process transaction database.And perform filtering to get the association rules that meet the item constraints.Finally,the coating process knowledge is extracted from the obtained rules and stored in the knowledge base.The test results show that this method improves the performance of the algorithm while shortening the calculation time of the algorithm.The proposed PCA-improved item constraint association rule algorithm is superior to the traditional algorithm.(3)A method for acquiring knowledge of ship coating defects based on rough sets is proposed.Based on the interactive acquisition of the relevant knowledge of coating defects,hazards,and processing methods,a knowledge acquisition model based on rough sets was established.This model realizes automatic acquisition of defect diagnosis knowledge from the original case by establishing decision tables,discretization of continuous attributes of decision tables,attribute reduction,attribute value reduction,knowledge classification and storage.The acquired knowledge coincides with the defect cause knowledge acquired interactively,which verifies the validity of the model.(4)A knowledge acquisition and management system for ship painting technology was established.This paper introduces the coating process knowledge storage and reuse technology based on the process database,and designs the system function framework.Based on the programming language and the above knowledge acquisition technology,the development of the ship coating knowledge acquisition and management system is completed.