Handling missing values and unmatched features in a CBR system for hydro-generator design

• Case base is constructed based on domain ontology to improve retrieval efficiency.
• Case representation is proposed and cases are represented by a unified tree model.
• The cost function is proposed to measure the semantic difference between two cases.
• The similarity function is defined based on the cost function.
• Experiments are executed to evaluate the performance of the proposed CBR system.

Hydro-generator design is a complex problem and case based reasoning (CBR) can improve its efficiency, but there are missing values and unmatched features which decrease the accuracy of CBR. In order to solve the problems brought by missing values and unmatched features, a similarity measurement is proposed by improving the edit distance which is widely used as a similarity measurement. In the proposed CBR system, the case base is constructed based on domain ontology to improve the retrieval efficiency. Then a case representation is proposed and cases are represented by a unified tree model. Next, by combining the edit distance with feature weights and the semantic meanings of case nodes, the cost function is proposed to measure the semantic difference and the conditions which make it a metric are discussed. Lastly, the similarity function is defined based on the cost function. A case study is presented to illustrate the use of the proposed CBR system, and then the experiments are executed to evaluate its performance in dealing with missing values and unmatched features respectively. The results validate that the proposed CBR system can handle missing values and unmatched features effectively.