Product configuration design is a knowledge intensive process during product development. It is a critical step as the cost and quality of a product is based on decisions made at this stage. In the iterative process of product configuration design, customers and design engineers use different terms describing products which often results in misunderstanding. Based on the historical transaction records of customer requirements and design parameters, this paper proposes an Apriori-based data mining method to transform the implicit knowledge into explicit association rules. Three criterions, support, confidence and interestingness, are applied for the evaluation of the extracted rules. The effectiveness of the proposed method is illustrated with a case study of electrical bicycles. The results show that that the proposed method can be a promising tool for product configuration design.