Data warehouse (DW) is a powerful and useful technology for decision making in manufacturing enterprises. Because that the operational data often comes from distributed units for manufacturing enterprises, there exits an urgent need to study on the methods of integrating heterogonous data in data warehouse. In This paper, an ontology approach is proposed to eliminate data source heterogeneity. The approach is based on the exploitation of the application of domain ontology methods in data warehouse design, representing the semantic meanings of the data by ontology at database level and pushing the data as data resources to manufacturing units at data warehouse access level. The foundation of our approach is a meta-data model which consists of data, concept, ontology and resource repositories. The model is used in a shipbuilding enterprise data warehouse development project. The result shows that with the guide of the meta-data model, our ontology approach could eliminate the data heterogeneity.